Deepai text generator

Now that Artificial Intelligence Can Write, Does Composition have a Future?

The title of this essay isn't the analogue equivalent of clickbait. I'm not trolling for a chance to up my K score. I really believe that Artificial Intelligence has gotten so good at generating prose and is so cheaply and widely available now that it is about to disrupt our discipline. I don't think composition is about to go the way of Classics and cursive, but I do think anyone with basic computer skills can now have an AI text-generator write essays, blog posts, sales copy, even letters and poems for them. As a result, we need to start rethinking what writing is, what writers do, and what writing instruction needs to become. By extension, AI's ability to write will have a significant impact on the humanities and the social sciences. They will also disrupt software engineering as they can write code as well as they can write text.

There has been a fair bit of hand-wringing in the press lately about the arrival of text-generators: "AI bot that can do schoolwork could 'blow up' US education system;" "The College Essay Is Dead Nobody is prepared for how AI will transform academia;" "The End of Highschool English;" " Google's new prototype AI tool does the writing for you." While asking, "does composition have a future?" is obviously sounding an alarm, angst is not the spirit in which I am offering the following exploration of AI's capacity to write. I'm taking a cue from Chris Anson, who has asked, "Instead of darkly subverting the human invention and writing process, how might NLP systems support the disparate goals and activity systems of different contexts?"

In what follows I will show how some professional writers have been using AI to enhance their writing processes , offer a few examples of it influencing mine, give direct evidence to support the assertion that "AI can write" (with a few caveats), briefly explain how AI writes, and offer some preliminary thoughts on what ready access to inexpensive AI text-generators might mean for the discipline of composition.

But first I want to practice a bit of traditional ethos-building to support my assertion that I am not some outsider trolling strangers for attention and to explain more fully my point of view on the AI-enabled future of writing.

Author's Curriculum Vita

I was a bored but academically ambitious (B+) English Major in 1984 casting about for something different from the classes in British, American, and Canadian literature that filled my calendar at the University of British Columbia when I came across a class called "The Rhetoric of Fiction" offered by a Professor I hadn't heard of, Nan Johnson. I think it was the word rhetoric that caught my eye. I didn't know what rhetoric was or how it might relate to fiction, though I kind of thought they might be synonymous or made to seem so.

I remember writing a term paper about Wayne C. Booth's The Rhetoric of Fiction and Vladimir Nabokov's Pale Fire. I remember nothing else about the paper, but I vividly remember that Nan Johnson taught me more about essay writing in that class than I had learned in all of my previous classes.

Nan Johnson showed me what rhetcomp could do for a thoughtful person struggling to be articulate, but if it weren't for spell-check, graduate school would have eluded me. Because I never learned to spell or proofread efficiently (dyslexic-like, I transpose letters), my grades were only ever on the cusp of excellence. In 1985, when the sound of me pounding on an inherited Clipper Portable typewriter finally overcame his patience, my roommate escorted me to UBC's public computer lab (I didn't know there was one) and introduced me to the Michigan Terminal System's word-processor. I learned to word-process, discovered spell-check, and got into Grad school. Word-processing changed my style. My sentences got longer, more flexible, accretive, and sometimes a bit meanderly. Revision was so much easier on a screen, even in the days of green screen terminals. Most importantly, however, I had more time for reading, drafting, revising, and editing because I didn't need to spend hours proof-reading from the last word to the first and then retyping everything, not to mention not having to literally cut and paste over typos left in a re-typed fair copy. I couldn't wait to get my own computer.

I've been teaching rhetoric and composition for nearly 40 years. I'm neither burned out nor disillusioned -- I've published more in the last ten years than in the twenty plus years prior. I am in no way inclined to suck my teeth and mutter video-playing-tiktoking-kids-these-days. I'm not offended by txt spk or upset by the tl;dr way of life most literate people live today because of our phone habit and perpetual access to new information. (Digital Shallows).

I am, I think, an early adopter with only a trace of pre-digital accent. I emigrated from analogue in 1995, teaching myself HTML and then CSS and then PHP and MySQL, and I've been designing my own reading, writing, and learning environments since the turn of the century, encouraging various kinds of humanities majors to explore web-based communications as a potential career path. I've taught more than a few the basics of web-coding. Along the way I have been paying close attention to writing-assistance technologies.

Spell-check was just the beginning, of course. Now we have autocorrect, blue pencil advice on the fly, and swipe-to-complete. I tend to ignore "swipe-to-complete" suggestions when I'm writing because they feel like an invitation to cliché. Sometimes I'll even recast a sentence just to spite the machine. If it hadn't suggested I complete the sentence in the way it did, I probably would have completed it that way. But since it did, I sometimes feel like I need to find an alternative. Perhaps my pre-digital accent is thicker than I want to admit.

The reply emails I receive sometimes seem not so much written as phrase-selected from a list of options, the kinds of options I tend to decline when replying. These apparently canned responses always strike me as overly enthusiastic, too exclamation-marky, but they aren't obtuse or irrelevant and many of my email correspondents are enthusiastic young people. I can't help wondering if selection from options is something other than writing, not that it matters as long as we understand each other. And anyway, I don't know if they or the machine wrote what I read. So the point is moot.

Although the learning environments I write for my students don't automate any of their tasks and only a few of mine, I've been watching composition automation developments closely.

Essay-grading software has been up and running since the 2010s, at least at the bureaucratic level of placement testing, like ETS. Short essays of a more or less uniform structure on a general topic are perfectly suited for machine graders because they only have to analyze diction, syntax, grammar, and paragraph structure. Given a limited kind of input, a machine can provide inter-rater reliability commensurate with any calibrated group of writing teachers. And the machine can process thousands of essays a minute since it doesn't have to read (it's calculating), to say nothing of giving feedback or offering revision advice.

Since I am more interested in teaching than summative assessment, and I don't have to grade a lot of 500 word essays on general topics, I never took more than a casual interest in AI graders. I found the prospect of automated writing more interesting, even fascinating, because to me it seemed impossible. I looked in from time to time but remained convinced that headlines like, "AI deemed 'too dangerous to release' makes it out into the world" (Griffen) were just made-you-look hyperbole. They were in 2019 when Griffen made that announcement. They aren't quite that now.

In an interview with Connie Loizos at Tech Crunch (link published and accessed Oct 29, 2022), the venture capitalist James Currier asserts that, "Every 14 years ... we get one of these Cambrian explosions. We had one around the internet in '94. We had one around mobile phones in 2008. Now we're having another one in 2022."

He goes on to say that text generating algorithms, were

pretty fragile, pretty brittle, up until about a year and a half ago. [Now] the algorithms have gotten better. But more importantly, the corpuses of content we've been looking at have gotten bigger because we just have more processing power. So what's happened is, these algorithms are riding Moore's law -- [with vastly improved] storage, bandwidth, speed of computation -- and have suddenly become able to produce something that looks very much like what a human would produce. That means the face value of the text that it will write, and the face value of the drawing it will draw, looks very similar to what a human will do. And that's all taken place in the last two years. So it's not a new idea, but it's newly at that threshold. That's why everyone looks at this and says, 'Wow, that's magic'.

What looks "very similar to what a human would produce" will be indistinguishable soon. In specific settings, it already is.

Turing's Test

My interest in AI generated prose (what we might call computational composition) was piqued on March 7th, 2015 when the New York Times published If an Algorithm Wrote This, How Would You Even Know?. I was reminded me of something I encountered at Rensselaer Polytechnic in 1988.

As you probably know, the famed British mathematician and code-breaker Alan Turning hypothesized that if a machine could engage a person in a conversation without that person suspecting their interlocutor was a computer, then humanity would have achieved artificial intelligence (Turing). One of the earliest attempts was the Rogerian psychotherapist expert system called Eliza, written in by Joseph Weizenbaum at MIT between 1964 and 1966. Eliza printed non-judgmental, open-ended questions to a screen in response to input from a user, creating the illusion of conversation. The machine had no "knowledge" but was simply pattern matching, key-word searching, and then asking an open-ended question that would seem relevant and perhaps even thought-provoking. I'm making this illustration up but it is representative.

Hi Eliza
How are you?
I'm bored.
Are you bored or are you lonely?
I think I'm bored
What makes you think that? // vague words like "that" are especially helpful in this context because "that" can refer to nearly anything. The computer doesn't need to know what the subject of the previous sentence was. Knowing the subject of a sentence was hard in 1964. It is not now.

For people unaccustomed to anthropomorphizing a computer terminal, the effect was momentarily astonishing. Eliza more often than not failed the Turing test, but it pointed towards one possible future (Wooldridge). Although expert systems like Eliza can't learn on their own, they can be taught in the sense that a programmer can write new lines for the script that animates them. Discovering how to get machines to learn on their own occupied many computer scientists for the next 60 years.

Fast forward to the present moment and most of the expert systems we encounter on websites are script-driven. Given a limited number of predictable closed-ended questions, you don't need an AI generator to make a user feel heard. Think of an FAQ. The paper representation of this rhetorical genre is question, answer. The reader scans the list of questions until they find the one they want answered and then they read that answer. They don't have to read a lot of irrelevant information to solve the problem they were looking to solve. The basic digital version of an FAQ is a list of questions the answers to which are revealed on click or hover. The dramatized version is a chatbot, a window within a window where a user submits a question, frequently from a list of possible questions, and an answer is returned. The fancier chatbots aren't script-driven. They use Natural Language Processing to "read" the question and thus return an appropriate answer. Digital FAQs and basic chatbots are more animation than automation. The answer isn't created, just hidden from view. These scripts can include pleasantries and often address the user by the name the user offered when prompted at the outset of the "conversation," but they do not communicate in any traditional sense, although a novice user might think they are interacting with a person. Given the increasing frequency of their use, it was forward thinking just four years ago to recommend bot script writing as a rhetoric and composition assignment, as Jeremy David Johnson suggested in 2018.

However, OpenAI just (November 2022) released ChatGBT, an AI focused on engaging people in conversation in a pretty sophisticated way. It can "answer followup questions, admit its mistakes, challenge incorrect premises." Most importantly, perhaps, it can reject inappropriate requests, making it closer to troll proof, a problem many chatbots have failed to avoid. (https://openai.com/blog/chatgpt/). It can, in other words, engage anyone in a "conversation" about anything. A typical chatbot works only because it functions within contextual constraints. You can't ask your internet service provider's chatbot if you should make dinner early tonight or go for a walk. Mind you, your internet service provider doesn't want to offer conversation. It just wants to solve its users' problems and sell its products.

Despite ChatGBT and the others following shortly, I still think writing scripts for bots has compositional value, since it makes a person anticipate and answer questions in a systematic way, not unlike stasis theory from rhetoric's distant past. However, bots no longer require scripts, and therefore there may no longer be any real-world value in learning to write them. The digital world changes so fast that this year's innovations may be obsolete in a year or two. Again, I'm not pulling the fire alarm to disrupt classes. I'm being calmly pragmatic.

While the Turing test focuses on conversation, the New York Times' "Did a Human or a Computer Write This?" offers a relevant test for AI text-generators (perhaps we can call that kind of writing computational composition). If we mistake for human a bit of computer-generated prose, the AI that wrote that prose passed the test. That doesn't mean, in my mind at any rate, that the machine will have attained intelligence, let alone sentience. Anthropomorphism is less rhetorical figure than it is a failure of critical thinking in the era of deepfakes and auto-generated images and texts.

The NYT's test presupposes that the person reading the given text doesn't know in advance if a person or a machine wrote it. In what follows, I know all but one example was machine-generated. So my test, I'll call it the rhetcomp test, isn't just pass/fail. I'll use the following rubric: an "A" auto-generated text is one I think would pass for human without suspicion. A "B" text might pass for human but has imperfections more or less consistent with a human rough draft, the less consistent, the lower the "B". A "C" text is only coherent enough to trick the innocent, people who don't yet realize that machines can now write coherent prose or those who don't care about authenticity or provenance. Assigning a "C" is tricky because the kind of word-salad a sleep-deprived, greatly preoccupied undergraduate might write off the top of their head moments before a deadline can read like something not quite conscious. Any text that fails the rhetcomp test lacks cohesion, has broken structures, weird word juxtapositions, pointless repetition, pat or cliché transitions that don't move the subject forward, vague words, strange digressions, writing that is inarticulate in uncanny valley ways.

Learning how to blind-identify "A" computational compositions is currently impossible because AI texts aren't copied from online sources. They are created. Some day there may be a repository of AI texts that could be searched like Google searches the web. But that day hasn't yet arrived. "B" level texts are interesting in that an honest writer might use an AI-generated text as a legitimate drafting procedure -- I do a bit of that in what follows. Getting a computational composition from "B" to "A" would involve human revision and the result would be AI-assisted human composition. Distinguishing word-salad from uncanny valley might be hardest of all AI-world literacies and far more critical in terms of student development -- assuming we retain old-school composition goals. We might modify those goals and show students how to edit machine-generated texts. Or we might revert to recitation. I will return to these thoughts in the conclusion.

Having to ask, "Did a machine or a person write this?" will change how you relate to reading and writing in profound and unsettling ways. Knowing that a machine wrote something when there's no textual evidence it did, that's more than unsettling, at least initially. I think we all need to get used to it.

We'll look at a range of AI generated examples that I think pass and a couple that don't in a moment, as a way of trying to think about how to identify indications of machine origin and how to make best use of their affordances, but first I want to offer indirect testimony to the potential utility of computational composition from the recent past, from before the AI "explosion" that happened in 2020.

AI and Writerly Professions

Journalism was one of the first writerly enterprises to foresee the potential in AI. Thomson Reuters started "injecting AI and machine learning into [their] value creation and delivery stack" in the early 1990s. (link). One of their current businesses is Westlaw Edge Quick Check:

Simply upload a brief and Quick Check will produce a report with recommendations for additional relevant authority, warnings for cited authority, an analysis of quotations, and a table of authorities.
Use this in-depth analysis to jumpstart your research, strengthen your arguments, pinpoint weaknesses in your opponent's positions, and compare multiple filings from a matter. (link)

The American Bar Association was encouraging legal firms to adopt AIs as early as 2017 .

The Associated Press was also an early adopter. They started using various tools to automate various processes in 2014.

The Associated Press was one of the first news organizations to leverage artificial intelligence and automation to bolster its core news report. Today, we use machine learning along key points in our value chain, including gathering, producing and distributing the news. ... Our objective in production is to streamline workflows to enable our journalists to concentrate on higher-order work. This ranges from the automatic transcription of video to experimenting with the automatic-generation of video shot-lists and story summaries. We also currently automate stories in both sports and corporate earnings. (link)

A year later, in 2015, the NYT had developed a word-processing environment that provided automated background research in real-time, as their journalists wrote.

"This prototype is comprised of a simple text editor (shown on the left), supported by a set of networked micro services (visualized on the right). The micro services shown here are recurrent neural networks (using https://code.google.com/p/word2vec/) that are trained to apply New York Times tags to free text, but you can imagine a host of other services that could do things like try to attribute quotes or that know about specific domains like food or sports. As the journalist is writing in the text editor, every word, phrase and sentence is emitted on to the network so that any micro service can process that text and send relevant metadata back to the editor interface. Annotated phrases are highlighted in the text as it is written. When journalists finish writing, they can simply review the suggested annotations with as little effort as is required to perform a spell check, correcting, verifying or removing tags where needed. Editor also has a contextual menu that allows the journalist to make annotations that only a person would be able to judge, like identifying a pull quote, a fact, a key point, etc." (link)

The NYT's Research and Development wing has since moved on to even more remarkable things, including a tool that inspects video to see if it is real-time or edited to represent something that didn't actually happen as though it had.

The Night Foundation began "exploring the intersection of AI and the news" in 2017 and now see it as "one of the forces that journalism can't ignore." (link)

Anyone who writes relatively formulaic data-driven narratives, sports writers, corporate reports writers, and so on, have probably come across a narrative generator that can produce a convincing first draft with no human intervention. The AI writes the story based on the data it gathers.
In pseudo code that might be something like:
Data input : Team A favored to win by 20. Team B score 4. Team A score 3. Last score happened with 10 seconds left.
Output: Team B beats heavily favored Team A in nail-biting upset.

United Robotics offers a suite of AI tools that will not only generate stories about sporting events but send interview questions to players and then represent and build on the interviews. Their tag line is "United Robots offers Content-as-a-Service, which means we build the robots and send the automatically generated content they produce straight to your CMS, sites or apps." That's impressive. If they can do what they claim, they are at the cutting edge of data-driven narrative automation.

Admittedly impressive, if it works as advertised, but can an AI write a story that isn't "just" data dropped into a formulaic narrative selected by pattern matching?

Here is the pitch from one narrative generator:

DeepStory is built around the cross pollination between human creativity and artificial intelligence to create extraordinary AI driven stories and screenplays. DeepStory removes the limitation of human imagination by allowing users to co-create with AI engaging movie scripts, RPG scripts, short form content, and stories of all shapes and forms. DeepStory AI creates human-like writing based on your input, enabling anyone to write quality stories. Whether you're a storyteller, screenwriter, gamer, content creator or an ad agency, with DeepStory you'll never be limited by your imagination! (link)

"Removes the limitation of human imagination"!? A bold assertion. A less dramatic assertion is that tools like these can minimize writer's block. I will offer an extended example of how an AI might facilitate invention in a moment, but first a quick word about the method I used to acquire the following examples.

A Quick Word about Method

About 15 years ago I set my Google News bot to notify me whenever anything related to artificial intelligence in general and computational composition in particular was published in the journals and blogs its algorithms track, as well as other topics I'm interested in. I'm not obsessed. In the last year and a half I noticed a tremendous increase in pitch and frequency of AI related articles, leading me to think AI has become the brave new tech of the day, like bitcoin for artistic types, perhaps. I decided to take a closer look. I've written what follows as though I am writing lab notes, real time observations. I did that to model one way of thinking about AI composition tools. But I also wrote it that way so you can see how I went from intrigued skeptic to cautiously optimistic novitiate.

It turns out that there are dozens of services offering various forms of AI text-generation. And there are more coming almost daily. Given the number of very different AI services and the fact that any list is out of date quickly, I decided to limit my sample to the first several screens Google offered when I entered "AI text generators" (see appendix 1). Letting the algorithm select samples kept me from following recommendations or sales pitches or even just responding to the appearance of a given website. I put that list in a file and wrote a bit of PHP script to randomly present me with one each time I went to the URL I created for it. So when I encountered the evidence I am about to present I was using a random sample drawn from an algorithmically generated list. I did not cherry pick this data in order to prove or disprove the assertion that AI can write. It is therefore a matter of chance that the first example I tested was the worst. It also explains why I didn't arranged these examples from worst to best, to fake a journey of digital enlightenment. There's good; there's bad, and there's wait, what?

Okay, AI Can Facilitate Writing, but can it Actually Write?

One of Deepstory's rival narrative automation services is InferKit. I went there and offered it the following prompt: "This was the first time she had seen a frog up close." I am not sure why that was the first phrase that came to mind. As I hit the send button, it occurred to me that I was channeling the frog/prince trope. Before I could wonder why, the machine came back:

She picked up the frog and said, "Ooh, look at this little guy.
What's your name, little guy?
Is that why you want to marry me?"
By Sunday, they had become "official" frogs and Mrs. Hoppy was pretty sure they would get married.
By Monday, she had re - named the frog and had a white dress for the frog and some black shoes, to match the frogs shiny black eyes.
All week, she was asking Mrs. Hoppy if she could play with her frog.
Monday night, Mr. Hoppy found out about their plans.
"No, Babe, it's not appropriate for kids your age.
You need to get a babysitter, "he said.
Mrs. Hoppy ....

Hardly convincing (a bright red "F" on the rhetcomp test). The use of quotation marks is bewildering, but more importantly, there are leaps in the dialogue: "What's your name, little guy? Is that why you want to marry me?" Wait, what? The frog didn't answer and it is hard to imagine how any answer to that question could lead to the follow-up question, "Is that why you want to marry me." It gets weirder. "By Sunday, they had become 'official' frogs ... By Monday, she had re-named the frog and had a white dress for the frog and some black shoes." Wait, they are both frogs now? What's an "official" frog? Who is going to wear the dress and shoes? What is the narrator's point of view? And why has it gone soft-core from there? Hard to imagine a person writing this.

If what Inferkit produced when I gave it the prompt I did was state of the art of computational composition, I would consider text generators still pre-emergent. Where's the "magic" James Currier announced?

By the way, there's a interesting documentary about a trying to make a movie from an AI generated screen play (Weiss). It's a script plagued by weirdly irrelevant action, making fun of the ineptitude of AI while simultaneously taking its future possibilities seriously.

EssayAILab was the next AI writer I was randomly presented. Since it wasn't promising narratives specifically, I wondered what it would offer if I asked it to write about an academic subject. I gave it just one word to work from: "Rhetoric." I had very low expectations. It instantly returned with these two alternative opening paragraphs.

I was startled by how readable and "informed" both of those were. My first assessment was that EssayAILab hadn't merely passed the rhetcomp test but gotten a solid "A". After reading the first paragraph a couple of times I thought I started to notice what I took to be structural issues, introducing Aristotle in the middle of the paragraph rather than starting a new one, for example. Each sentence is articulate on its own, but the order of presentation seems a bit arbitrary. If a student handed this in as a draft I would suggest adding a couple of line breaks after each sentence, to make each seems like a topic sentence, and then asking the student to see if each might be developed into it's own paragraph. I would also suggest scrambling the sentence order to highlight the lack of internal cohesion -- I have a script that will reorder the sentences in a given paragraph and students, and I, find that a helpful way to ruminate on the relationships among ideas. But all of this reflexive writerly advice assumes a human wrote the paragraph. A machine wrote this paragraph in a nano-second with just one word and no context for guidance. Wow.

The second paragraph offered by EssayAILab seemed to me more cohesive, and even more startling in that the expression "underwent a shift from speaker or writer to auditor or reader" suggests a plausible take on how 20th century rhetoric really can be said to differ from its classical ancestors. One would have to unpack that idea fully to make it entirely convincing and even then it would be imprecise given that seeing rhetoric as structural and systemic is arguably the 20th century's larger contribution. Still, from rhetoric to reader response criticism in a nano-second? Impressive, machine.

Since what I just entered into evidence might seem to you as it seemed to me like rhetorical magic, I'll spend a couple paragraphs trying to explain how AI writes, and why it has recently started passing for human, to the extent I can since the companies offering these services are black boxes and I am neither a computational linguist nor a statistician by trade.

How AI Writes: Statistical Magic

I wrote an earlier draft of this section using Google and my own powers of synthesis, summarization, and citation. I was dubious about the results because I'm not a statistician by any means and what I wrote just seemed muddled. So I asked ChatGPT to explain the key words to me (AI Paramater, NLP, LLMT). Doing that turned out to be much more efficient than the old way of summarize, quote, cite. The lucidity of its explanations made me realize I was conflating Natural Language Processing with Large Language Model Transformers. It also showed me how much more efficient one might write using tools like these.

Natural Language Processing is a field of artificial intelligence that uses statistical methods to analyze word frequencies, word clusters, sentiment analysis, and text summarization to, among other things, predict what word would most likely come next in a sentence.

How would you complete the following: peanut butter and ____. ? If you are an English speaking American, you would probably fill the blank with jelly. If you are an English speaker from a different culture, you might have come across peanut butter and jelly and so would accurately make an informed guess. But if you had never seen the expression, there's no telling how you would fill in that blank. Perhaps you would offer ¯\_(ツ)_/¯. Or just leave it blank.

Given strict control over input, it is relatively easy to provide plausible outputs. I've written a couple of auto-graded multiple choice tests using this kind of very basic logic, for example. As with all multiple choice tests, there's a question and a set of possible answers one of which is right. So if a student bubbles in clicks A and the answer is B, the machine increments the grade by 0. If A, then grade increments by 1. This simple process works fine but it lacks subtilty. What if answer C is not quite right and not quite wrong? If you, a human, want to achieve that level of sophistication, the hard thinking happens in how you phrase the possible answers. The logic that increments the grade by .7 instead of 1 is trivial: If A, increment grade by 1; if B, increment grade by 0; if C, increment grade by .7; next.

In this example, the machine's part is trivial because all the work is done by the person composing the test. Could a machine compose as well as grade such a test?

AIs use statistical calculations about the probability of an outcome to choose the most likely from among all the possible outcomes, what statisticians and social scientists call the sample space. They do this by first defining the sample space in, ideally, effective ways. How many different ways can you fill in the peanut butter and blank?

In pseudo code that might be something like: Given an American audience, jelly probably completes peanut butter with a reliability co-efficient of close to 1. There are other ways a person might complete the phrase but they would be uncommon or even idiosyncratic. In pseudo code that might be something like: If the audience isn't English speaking American, search for similar food items from user's cultural and linguistic background -- any web browser (and any app on any phone) knows the primary language and cultural background of any given user. But how does a machine get from peanut butter and jelly to, say, humus and pita?

The way humans use language is of course complex. Writers have to consider vocabulary, denotation, connotation, style, syntax, grammar, genre, sentence length, sentence complexity, tense, context, sentiment, voice, and audience, which itself has components since not all people receive even the same message in the same way. Many variables, in other words. This complexity is why learning to write well is so time-consuming for both the learner and their teachers.

Perhaps the most commonly known Natural Language Processing model is the N-gram. The N in N-gram refers to the number of consecutive words sought in a given string of words. So the N for peanut butter and __ is one. If we want to complete peanut butter ___ ___ we would be looking for a bi-gram, a gram where N is 2.

If you go to Google's n-gram viewer (https://books.google.com/ngrams/) you can see an application of n-gram in action. Type in the expression Rhetoric and Composition, for example, and Google searches through all of it's corpus (consisting perhaps of as many as 130 million books) for the string "Composition and Rhetoric", counts the number of times the phrase appears in each year, and then returns the year with the highest frequency. The phrase "Rhetoric and Composition" peaked in 2004. This is an example of analytic as opposed to generative AI. If we could flip that around and ask Google to complete the phrase "Composition and ___" asking for just one word, we would definitely get Rhetoric in 2004 but perhaps not before or after that. N-gram viewer can't do that for us, however, because it is an analytical rather than generative AI. But of course Google has generative AIs as well.

Google started using predictive search to speed up your Googling in 2004 and renamed it autocomplete in 2010. That technology has increasingly become a part of all our writing applications since then. The "Cambrian explosion" that made generative AI what it is becoming today happened in 2017 when Google's AI division, Google Brain, shared its Large Language Model Transformer (LLMT). < chatGPT>Large Language Model Transformer (LLMT) is a type of deep learning model that uses transformer architecture to process natural language. It is used for tasks like Natural Language Understanding (NLU) and Natural Language Generation (NLG). LLMTs are trained on large corpora of text and can generate more accurate results than traditional NLP models. LLMTs also allow for transfer learning, where a model can be fine-tuned for specific tasks or domains. </ chatGPT>

Transformers use self-attention mechanisms -- statistical methods -- to identify what is most relevant in a string of text. Transformer models are used to generate text, improve machine translation, and develop conversational AI agents. They are what made ChatGPT fill in the blank with jelly when I asked it, "Complete the following : peanut butter and ."

To give you an idea of the scale of change that happened in just a couple years, OpenAI's GPT-2 (2019) had 1.5 billion parameters. GPT-3 (July 2020) has 175 billion (Tamkin and Ganguli). <AI - Hyperwrite >AI Parameters are the settings that decide how a computer program makes decisions. They tell the computer how it should weigh different pieces of information and decide what to do. For example, if a computer program is trying to decide what to do with a picture, the AI Parameters might tell it to focus on the shapes and colors, or the faces in the picture.</Hyperwrite - AI>.

A sophisticated AI writer can refine its understanding based on input from a user about its output. This is known as guided AI. Transformer AIs use unsupervised or deep or machine learning, where the AI can draw inferences and then assess their accuracy and refine the inference engine without human participation. The really powerful AIs can learn new skills with nearly no instruction. OpenAI basically taught itself French, for example (Stanford).

They learn by means of neural networks. I knew that, but I wasn't sure how to explain it, so I asked ChatGPT: < > A neural network is a type of artificial intelligence (AI) that is designed to recognize patterns in data. It is composed of many connected units called neurons, which work together to process information and make predictions or decisions. Each neuron receives input from other neurons, processes that information, and sends output to other neurons in the network.
For example, a neural network might be trained on a large dataset of images of various objects, such as dogs, cats, and cars. As the network processes each image, it uses the connections between its neurons to identify patterns and features in the data. Over time, the network learns to associate certain patterns with specific objects, allowing it to accurately classify new images it hasn't seen before. /< >

One self-learning technique uses what is called a generative adversarial network. This technique pits a generative neural network against a discriminative neural network. One machine makes something and the other critiques it based on a model given by the programmer. Basically the human shows the discriminator what the intended output should be and the generator is given random data to start with. It makes something. The discriminator tests it against the model, then both refine their efforts and it goes again, ideally until the generator produces an example the discriminator can't find fault with. wiki Kind of like graduate school.

In pseudo code an image generator AI would be something like:
Programmer to discriminator: This is an image of an apple.
Discriminator to programmer: got it.
Generator to discriminator: This is an image of an apple.
Discriminator to generator: it deviates from appleness in these ways.
Loop until image of apple ≈ image of apple.

While looping, the generator gets better at generating and the discriminator at discriminating based on each one's separate experience. Cool, for sure. But given how many varieties of apple there are and how an Apple product isn't an apple at all and neither is an apple of your mother's eye, not to mention the fact that the "apple" Eve ate was probably a fig, assuming there was an Eve in the first place, and you can see how "magical" Natural Language Processing seems when it seems to work.

Imagine the process for getting a neural network to generate a haiku worth reading. The model has to contain the rules of the genre haiku -- 17 words max, 3 lines, first line 5 syllables, second line 7, third line 5. That's simple enough but given only that one would get a lot of noise, monkeys banging on old-fashioned typewriters. So the neural network also has to be able to understand (calculate the probability of) how words and sounds and linguistic images and reader sentiments interact to create a haiku resembling a compelling model. The more critic-approved haikus in its original dataset, and the better the inferences it can draw from that set, the more impressive the results. A sonnet has similar structural requirements, so it could perhaps be similarly successful. But what of free verse?

Given the level of complexity, Natural Language Processing requires a great deal of interdependent stochastic decision making and to accomplish this, neural networks are written, multiple layers of algorithms (decision making processes), each layer processing a different element quickly and then passing the result on to the next layer; specialization enables speed and accuracy:

Once an input layer is determined, weights are assigned. These weights help determine the importance of any given variable, with larger ones contributing more significantly to the output compared to other inputs. All inputs are then multiplied by their respective weights and then summed. Afterward, the output is passed through an activation function, which determines the output. If that output exceeds a given threshold, it "fires" (or activates) the node, passing data to the next layer in the network. This results in the output of one node becoming in the input of the next node. This process of passing data from one layer to the next layer defines this neural network as a feedforward network. (link)

The way we get from peanut butter and jelly to humus and pita is to make hundreds of thousands of statistical calculations in a series until all of the given parameters have played out and a probability as close to 1 as the machine's tolerances have been instructed to pursue has been discovered. Those parameters would likely include such things as language, nation, culture, food ways, common dishes. I'm just illustrating here. I have no actual idea what any of the millions of parameters any AI might use are. I can say this without shame because of what people in the industry refer to as "the black box problem." As Ella Alderson puts it, "we may understand the input, we may understand the output, but the AI's decision-making process which bridges these two is a black box we can’t seem to peer inside."

Given the complexity of human communication, the fact that a machine can accurately predict your next word is remarkable. That it could write a sentence or a paragraph or an entire essay for you given just one word as a prompt is, well, magical. But words that pass for magic, as Plato explained in Phaedrus and Derrida reminded us in Pharmakon, are ambiguously efficacious.

Garbage in, Garbage Out

The investment required to create an AI writer is substantial, upwards of $10 million, according to Vinay Ilyengar. While this initial cost limits participation at the development level, OpenAI and others (BLOOM and Eleuther, for example) have made their technology available to developers for licensing fees or for a stake in what is developed. Thus the power to generate entire paragraphs has overcome the barriers to entry that kept it in the hands of linguists, programmers, and people with direct access to venture capital.

One of the other requirements for computational composition is a readily available digital corpora. A corpus is simply a collection of texts, many millions of lines in some cases (Google Books, Wiki, the Guttenberg Project, to name a few), that are used to "train" the AI, a dataset from which it can draw inferences about how to interpret and compose, based on word frequencies, word clusters, regression analyses, standard deviations, and a lot of other statistical processes far beyond my understanding. The corpora available to AI writers is in theory limitless. Any text formatted for web delivery (HTML, XML) can be incorporated. Open AI's GPT-3, for example, currently uses 570 gigabytes of text. https://hai.stanford.edu/news/how-large-language-models-will-transform-science-society-and-ai

The training materials AI writers rely on is limitless in theory, but often the same set is used over an over again because plugging in existing data sets is much more efficient than finding, acquiring, formatting, and giving new material to the machine. As Kate Crawford explains in Atlas of AI, the biases and assumptions implicit in the training materials are embedded in that material and so are inevitably a part of what the machine generates. While new material is possible in the sense of recombination of materials in new ways, the legacies of the original remain only partially buried in the shifting sand of newly generated text. When Angela Fan, a data scientist for Meta, set out to auto-generate biographies of women scientists to contribute to Wikipedia using Wikipedia as her training dataset, she found that gender biases implicit in Wikipedia had to be overcome before the project could succeed.

Kate Crawford also points out that the environmental and social cost of providing the herculean computational power effective AI requires is arguably unconscionable. That is an important critique, although I only have space here to acknowledge it in passing. If at some future point AI becomes not merely unconscionable but unsustainable, then its achievements will be purely historical. Given the cyclical boom and bust history of AI, it's quite possible that the current boom will become an echo. I am in no position to predict what's next for AI. My goal is merely to persuade you that AI can write now and thus that you should think about what the implications of that current fact are. If you are inclined to wait until the whole thing blows over, content to assume it will, waiting is always an option, though not always an optimal option. As I write, we don't yet know if Twitter is dead or just stunned, but regardless of its fate we can't deny its history, good and bad, and we would be foolish not to learn what we can from what we currently know even if that knowledge like most things is temporary.

Rot can set in from the outside as well.

In 2016, Microsoft created a chatbot they called Tay, Thinking About You. They gave it a Twitter identity -- "The AI with zero chill." They gave it a Twitter handle, @TayandYou, and then they gave it to Twitter. People would respond to Tay's Tweets and Tay would use that information to Tweet a-new. Humans of Twitter were functioning like a discriminator neural network. Only they weren't so much discriminating as antagonizing and provoking. Sixteen hours later Microsoft had to shut Tay down because it was spewing racist, sexist vitriol. The Humans of Twitter trained it to be a Troll after their own image.

A similar thing just happened to one of Meta's AIs. The Galactica language model was written to "store, combine, and reason about scientific knowledge" (Edwards). According to Edwards, Galactic included "48 million papers, texts and lecture notes, scientific websites, and encyclopedias." The goal was to facilitate and accelerate the composition of literature reviews, Wiki articles, and the like. When Meta offered it to the world to beta test, some people found it promising but others found it problematic and some set out to vividly demonstrate its problems by feeding it prompts that led it to articulate nonsense, in some cases offensive nonsense, as though it were facts. Yann LeCun announced the off-lining of Galactica with a Tweet, "Galactica demo is off line for now. It's no longer possible to have some fun by casually misusing it. Happy?" (link), suggesting malicious human interaction rather than AI defects led to the problems Galactica exhibited.

These two examples suggest that if AIs are going to learn from their own creations and people who don't have a vested interest in those creations are allowed to meddle with them, then all of the problems humans are prone to will be echoed in the AI's creations. If an innocent person encountered something written by such an infected AI, they might take nonsense as fact and could then conceivably exacerbate the problem by feeding it more AI-inspired garbage. See also "On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? ( Emily M. Bender, et al. link). The moderators at StackOverflow, a coder's Q and A site heavily used by developers and novices, shut down ChatGPT, for giving bad coding advice.

In these cases the rubbish input came from malicious users, but the same effect was created when the Urban Dictionary taught IBM's Watson to curse like an internet sailor (wiki). Given that an AI writer could compose thousands of messages a second and instantly publish them on Twitter and Facebook and Instagram, to any digital space, you can readily see how disinformation and misinformation and meddling can be automated beyond most people's understanding. Good information could be spread that way too, but bad information travels faster and what well-meaning soul would think to weaponize good news?

So the results of unattended algorithmic composition can range from absurd to traumatic, indicating that human oversight or adversarial machines designed to offer as-good-as human oversight will likely need to become a part of AI's generative practices. Even if we don't know exactly how these machines do what they do, we need to much better understand the ways they can be employed, the limitations inherent in their models, and how we might both use and learn from the facility they can provide. All of which means, I think, that we need to be paying close attention to what these machines produce. And that means we need to remain calm.

Back to the Lab

In search of evidence that computational composition was still mostly hype, and starting to suspect I might be wrong, I hit resubmit on my random link presenter and it took me to Copy.ai. The word copy in this context refers to copywriting, like for advertising and blogging and other commercial purposes, not plagiarism. I'm reminded of Erasmus' De Copia, the compositional exercise of finding dozens of different ways to say the same thing in order to develop a more copious style. Anyway, I told Copy.ai I wanted it to write a blog post about an imaginary product I called "Rhetoric AI." Copy.ai also asked for a product description and so I gave it this: "An AI that uses the corpus of Harvard Classics to generate speeches like those of the classical rhetors of Greece and Rome." I asked for a "professional tone" from the many tones it offered. And hit send. It returned instantly with the following suggestions:

Rhetoric AI uses the corpus of Harvard Classics to generate speeches like those of the classical rhetors of Greece and Rome. This brings us closer to understanding how rhetoric evolved, how it works on a cognitive level, and how it continues to impact our modern world.

Interesting, maybe an "A"? But how could reading all the speeches and rhetorics in the Harvard Classical library tell us anything about "a cognitive level"? And how could it tell us how the modern world has been impacted by say, Pseudo Quint.? I guess I would say this is a "B" on the rhetcomp test. It's easy to imagine it was written by a human but one perhaps not paying close attention. Or then again maybe a "C" if "cognitive level" sounds a bit uncanny valley.

The machine's second suggestion was:

The Rhetoric AI is a groundbreaking ICT system that uses the corpus of Harvard Classics to generate speeches like those of the classical rhetors of Greece and Rome. The Rhetoric AI analyzes the texts, extracts body and voice characteristics, extracts speech devices and locates epoxy structure using a machine learning model.

What's an ICT system? Is that a bit of artificially generated nonsense or am I just not familiar with an acronym I should know? I was still pondering "voice" in this paragraph when I got to "epoxy structure." Pffft! That's a "D" on the rhetcomp test.

Here is the third suggestion:

Rhetoric AI is the application of machine learning to rhetoric and modern-day debate. Rhetoric AI uses corpus data of Harvard Classics to generate speeches, written by the classical rhetors of Greece and Rome, on modern topics such as: Brexit, Trump's America, Brexit and Trump, etc.

Uh, ok, never thought of applying this imaginary "Rhetoric AI" to Brexit and Trump, but upon reflection, speeches about contemporary, eye-captivating, topics makes a kind of sense that hadn't occurred to me until the machine suggested it. Were I keeping a blog that needed to attract thousands of eyeballs, Hmmm. I guess I would give this a "B" too.

There was also a fourth suggestion which I failed to notice because it was below the fold the bottom of the screen. Subsequent queries offered shorter suggestions and thus I noticed it offered four rather than three suggestions. But I will stick to showing just the first three because that's what I saw when I was experimenting.

To be clear, the product I called "Rhetoric AI" does not exist, and the product description I offered was an extemporaneous riff. I doubted Copy.ai would come up with anything useful because it had no frame of reference (I assumed) and wasn't written for scholars; it was written for content creators -- copywriters, bloggers, Instagram influencers, and so on.

If the above was what I got when I chose a professional tone, what would a "friendly tone" generate, and what might that tell us about this machine's sense of style?

Rhetoric AI is an AI that uses the corpus of Harvard Classics to generate speeches like those of the classical rhetors of Greece and Rome. The text data has been cleaned, converted into a structured format, and optimized for machine learning. The texts include many great speeches from Plato, Aristotle, Cicero, Augustine, and others.

If "cleaned, converted into a structured format, and optimized for machine learning" can be abbreviated to ICT, then it seemed to have made an apt audience-based rhetorical adjustment. I would give this an "A." But I wanted confirmation. When I Googled "the acronym ICT AI" I got:

ICT is an acronym for "information communications technology." Many people ask what is ICT. What is the meaning or definition of ICT? The acronym ICT is often used in many different contexts. ... (link)

That sounds like it was written by a lesser AI or a bored undergraduate, given the throat-clearing repetition and pat transitions like, "Many people ask." I'm inclined to think this was written by a machine and so give it a "D". Were it written by a person, I would have wished they revised it more before submitting it. But were the writer in fact a person they might respond, a bit testily, that they had written the way they did to ensure Search Engine Optimization, to make sure that a robot spidering the web would interpret the repetition of key words as evidence of relevance. "After all", I imagine the human author might say, "when you Googled, ICT, you got my blog post, right?" Fair play. So, did a machine write this for people? Did a person write this for machines? Did a machine write this for other machines? Or did a person write this for people without knowing enough (or caring) about writing for people?

Back to Copy.ai:

Rhetoric AI is a computer program that uses the corpus of Harvard Classics to generate speeches like those of the classical rhetors of Greece and Rome. It performs this task by studying the historical styles of Greek and Roman orators and applying it. [To what? Brexit, maybe.]

Rhetoric AI is on a mission to recreate the masterpieces of classical rhetoric by learning from their actual speeches.

That suggestion reminded me of the Open AI's Dall.e-2, which replicates famous artists' work. I was starting to wish that classical speech replication on current subjects was already a thing. Add the AI that can replicate a dead person's voice and we could have Cicero back among us. Ok, that will always be impossible because we have no Ciceronian audio to work from, but a facsimile, or a fake, based on words he used and the speeches and letters he wrote? Absolutely possible, especially since we have texts written for centuries copying his style with obsessive compulsion. (Erasmus, Ciceroneanus). If we created a corpus out of all his speeches and letters, a writing AI could create Ciceronian deep fakes. For an actual rendition of my day dream, see "The importance of being on twitter" written by Jermome K. Jerome, London, Summer 1897. (link).

Amusingly apropos, Meta just came out with an AI it calls Cicero. "CICERO: An AI agent that negotiates, persuades, and cooperates with people" (November 22, 2022). CICERO plays the board game Diplomacy, which requires both strategic analytical and generative AI. link

Here are Copie.ai's three suggestions for a "persuasive tone," all of which I would say pass the rhetcomp test, though they are very short and thus less likely to suffer from the cohesion issues noted above:

Rhetoric AI is an AI that uses the corpus of Harvard Classics to generate speeches like those of the classical rhetors of Greece and Rome. It learns by reading thousands of speeches from the ancient world such as those by Sophocles and Cicero, then writes new ones.

Rhetoric AI is a conversational AI that uses the corpus of Harvard Classics to generate speeches. The AI is designed to imitate the classical rhetors of Greece and Rome, by knowing the most direct and effective ways to get your point across.

Rhetoric AI is the world's first AI to match the rhetorical styles of ancient Greek philosophers, used to generate speeches like those of Cicero, Quintilian and Aristotle. Rhetoric AI generates powerful and persuasive academic content.

Copy.ai doesn't just generate text. It lets you revise, edit, save and generate more suggestions. It offers, in other words, an AI supported workflow, a contemporary take on invention, drafting, and revising. I didn't take my experiment that far. I merely asked it to generate new content with a different tone, and each time I noticed that it seemed to be offering more plausible output, like it was learning. Since all I did was ask for different tones, it had no idea what I thought of what it offered, so learning seems unlikely. Perhaps I was being seduced by the seeming rationality behind the text as it appeared as if by magic on my screen.

Nevertheless, by giving me different descriptions to ponder, the machine was helping me imagine what the as yet non-existent "Rhetoric AI" might become. It was, unwittingly, helping me brainstorm a nascent thought into a possible project. Eureka!

My very brief interaction with Copy.ai convinced me that this AI could be an effective writing companion, an aid to invention, a way to avoid staring at a blank screen. I wasn't convinced that an AI composer could eliminate the need for writers, but it certainly could facilitate writing by speeding up invention. I wondered what other AI writers could do.

Examples from several other AI services

My Assignment Help is a comprehensive automated writing suite in that it offers a number of tools, like plagiarism check, a paraphrasing tool, a referencing tool (Given an ISBN or title it will return the citation formatted in any one of eleven styles). There are also human "experts" available for consultation and perhaps hire.

In my estimation, this passes the test. It sounds very drafty, but I can imagine a person having written this. However, the "tip" in the highlight box is a big red flag: "This sentence has been taken from online sources." It seems this paragraph wasn't auto generated but culled without attribution. Examples like this aren't merely problematic. They are actually disruptive. They muddy the water of authorship while undermining the achievements of better AIs. We need to find and discuss examples like these in our writing classrooms and among ourselves.

When I entered the word "rhetoric" into Smoden Author, it requested more input so I added the word "philosophy" and I got the following:

When I first read that I thought it was a "B". It's not brilliant, certainly. The transitions seem pro forma and the order of the sentences seem otherwise arbitrary. Each sentence in each paragraph is saying kind of the same thing. Because I'm a little more familiar with computational composition now, I think this is a "C". If a student turned that in, would you be suspicious of its provenance?

The Good AI offered this fairly perfunctory start to an essay, albeit with just the one word "rhetoric" as a prompt.


Perhaps if one added a couple of example rhetorical devices it would beef up the outline into more of a drafty draft.

By contrast, PaperTyper offered this.

The first part of this is almost identical to the first suggestion offered by EssayAILab. That's interesting. I suspect they are using the same corpus and the same algorithms. The repetition makes me wonder how deep the AI's writing pools actually are. The second section, the one sub-titled "Scope" is much more compelling. I'm inclined to give this an "A". If I hadn't come across the EssayAILab version earlier, I would definitely have given this an "A". But now I'm thinking it has failed, more evidence that we need to spend more time becoming conversant with these machines.

At this point I decided to see what this brave new digital world could do with my pre-digital essay topic, "Wayne Booth's Rhetoric of Fiction and Nabokov's Pale Fire." I assumed that because this was very specialized, referring to specific authors and thus requiring some contents in the corpora relevant to Nabokov, not a stretch, and Wayne Booth, a much more demanding stretch, it might generate less impressive results. I wasn't wrong.

Smodin offered this:

Deepai.org offered this:

Neither of these strike me as heuristically valuable and I don't think either passes the rhetcomp test. Of the two, Smodin's version is clearly better. The opening line of the Deepai version sets off my AI alarm: "Wayne Booth's Rhetoric of Fiction and Nabokov' Pare Fire as "Songs Not in The Eye," I believe the writer in question is a man of many talents." What? I can't believe a human, no matter how far out to sea, would write this.

The Smodin piece is more superficially convincing. You would need to know a (very) little about both Booth and Nabokov to see right away that it was machine-generated. If one of your students turned this in, how would you respond?

When I asked PaperTyper.net's essay-editor to draft "Wayne Booth's Rhetoric of Fiction and Nabokov's Pale Fire" I got, "Oops, it seems we can't find anything for your topic. Change it or check spelling 😊" And below that, "Do you have a narrowly specialized topic? No big deal! Try custom writing from our experts 😉", followed by a big button that said "Order now." I tried various alternative formulations and got the same sly invitation to buy my way out of the rhetorical situation I had created for myself. Logographers rejoice.

Given how lame it's response was, I hypothesized that the problem was the complexity of the prompt and to test that I gave it what I imagined was an easy prompt. I fed it "Modernism", and it instantly returned a credible draft on Modernism.

From this very brief investigation I inferred that the more complex and arcane the prompt, the less compelling the results. A year or two from now they may be better able to handle greater complexity, as the adversarial algorithms refine their results and the corpora they draw on get deeper and deeper, assuming the business models change. As long as they remain merely an attractive lure for the distracted and under motivated they won't get much better. Why would they?

I didn't think it was possible yet, but what I saw convinced me that some AI can write well enough to pass for human. And even the ones that don't quite pass offer new ways to pre-write and brainstorm. Have I been spellbound? I don't think confirmation bias led me astray, but I was moving quickly through a small sample. I have only 19 services in my collection, chosen algorithmically by Google, and I only looked at seven of those. There are more AI services coming online all the time. I collected my sample in October, 2022. Google came out with "Wordcraft" in November. ChatGPT came out in December.

On Monday [December 28, 2022], OpenAI announced a new model in the GPT-3 family of AI-powered large language models, text-davinci-003, that reportedly improves on its predecessors by handling more complex instructions and producing longer-form content. Almost immediately, people discovered that it could also generate rhyming songs, limericks, and poetry at a level GPT-3 could not previously produce. (Edwards)

Since then, I am confident, more have come online.

The AI services I looked at range widely in terms of cost (most offer some kind of "free" trial), services provided, and intended audience. Some, like MyAssignmentHelper and PaperTyper seem geared specifically for students and might be little more than fronts for paper mills. Others seem to have content creators in mind because they offer to eliminate writer's block and speed up the writing process and given a correctly constructed prompt, they can keep their promise. These AI's range widely in terms of capacity. But the good ones will pass the rhetcomp test regularly.

Lest we think all of these AI's are directed toward copywriters and undergraduates, there's at least one company looking for graduate students and faculty. Elicit.org's pitch is:

Elicit uses language models to help you automate research workflows, like parts of literature review.
Elicit can find relevant papers without perfect keyword match, summarize takeaways from the paper specific to your question, and extract key information from the papers.
While answering questions with research is the main focus of Elicit, there are also other research tasks that help with brainstorming, summarization, and text classification.

You really should have a look at elicit.org. The website is dynamic and therefore needs to be seen to be properly understood, but I think it could greatly accelerate the process of writing a literature review if one were working in a quantitative field.

In Order to Write, You Have to Read

Many of these AI services, and there are many others as well, offer text summary, which makes sense because in order to predict what word is most likely to come next the machine has to "understand" what came before. Point it to a text, however long, and it will summarize it for you instantly. There are also sentiment analysis tools (eg), to suggest what mood the author was in, assuming it was human. Sentiment analysis is especially problematic for ideological, ethical, and legal reasons: Should robots scan blog posts in search of potentially suicidal people? Could a malevolent bot go looking for "gay" prose (Resnick)? Nevertheless, AI can read as well as write, which makes perfect sense, from a writing teacher's perspective.

My goal here isn't to make recommendations from among the AI tools I've explored, nor in any way specifically critique any of these AI writing suites. Nor do I want to engage here in the theoretical and ethical concerns I just raised. My primary goal here is to warrant my assertion that "AI can write" and to encourage others in our profession to spend time pondering these services, both as pedagogical opportunities (or threats if that's your bent) and possible writing companions.

Conclusions

Some AIs can write well enough to pass for human and they will get exponentially better in the next couple years. Perhaps by the time this essay finds an audience a significant portion of what you read will have been machine-generated. While the impacts of this fact will take a while to be understood fully and will be changing constantly, they do not spell doom for writerly enterprises. In fact if anyone should be nail-biting, it's Google. Why spend hours reading, synthesizing, summarizing and citing a myriad of sources when you can just ask ChatGPT to explain something to you so you can copy and paste? Google knows this well, of course. They gave Transformer to the world.

Headlines like "The End of High-School English" and "The College Essay is Dead" are mostly reationary. AI composers and text analyzers will not immediately render writing (or coding) skills redundant. Although they will enable unscrupulous and poorly supervised people to fake their own labor and exploit the labor of others, nefarious communication strategies are nothing new. Mostly what AI generators will do is accelerate invention and provide better editorial assistance than current digital tools can. Written a complex paragraph that seems both hard to read and maybe not quite on point? An AI digital writing assistant can probably fix that for you.

In addition to editorial value, these tools have tremendous heuristic value. They can analyze and summarize complex documents (even contracts). They can jump start a narrative or an argument by providing a writer with dots to connect, insights that had eluded them, new combinations of thoughts. They can greatly enhance what/if thinking. They can help with writers block, in other words. They can also accelerate the process of posting on social media and blogs and other places where volume and frequency matter more than originality. They will change the way we think about what writing is and what an effective writing assignment is, harnessing various AIs to create AI enabled and enhanced forms of communication.

But we also need to acknowledge AI's limitations and problematic uses. They are resource intensive. The corpora on which they are based may have been created on the backs of exploited workers (Chloe Xiang). Like a great many innovations, it can be said that, "AI Helps the Powerful but Harms the Vulnerable" (Shankland). They can generate eloquent nonsense, confuse and mislead people (how old school rhetorical of them). They function retrospectively, working on what has already been published. Thus they are prone to old biases. They can not think or create though they can recombine. They are synthetic and analytic but not creative per se. While I think it a maladaptive strategy, we might also point out that the disciplines of Artificial Inetlligence have continusously undergone boom and bust cycles and therefore it's not impossible that these tools will go away because they became unsustainable. They might get Twittered.

For those of us who are feeling paralyzed by the plagiaristic opportunities these facilities seem to enable, there are a number of policies we might implement. We might return to recitation. It's hard to elaborate on something you didn't write. We might require citations so that were a student to get an AI to write a draft, they wouldn't be able to just copy and paste it as ai-generators don't cite, not because they are plagiarizing but because they are creating new prose. A student who learned how to find sources to validate an AI draft would be engaged in a new kind of composition but composition nonetheless, I think. There are, however, AI suites that point to AI identified relevant sources and we might teach how best to use these. We should also acknowledge that not all writing needs to be authentic in the ways academics want. A lot of mundane writing tasks could be greatly accelerated by copy and paste strategies and we need, I think, to help our students learn how to thrive in such a world. We might also want to create a convention for identifying computational compositions <AI> that allows people to make open use of them, discouraging clandestine behavior by normalizing the use of AI analyzers and generators. We need to be vigilant about essay topics and probably should vet them through a strong AI generator to have a sense of what we might see before we see it. Remember that both CopyAI and EssayAI created similar responses to "rhetoric" as a prompt.

We who teach writing need to start paying close attention to how these tools work, how best to use them in our own work, and how best to help novice writers learn to use them effectively in contexts we ourselves have not experienced and aren't in a position to anticipate.

TL;DR

I think composition has a future but we need to start adapting now by spending more time looking into computational composition both as a method of invention and an object of rhetorical analysis. We also need to start thinking about how best to teach writing in an AI enabled and accelerated world. We are currently living in a truly new rhetoric.

Works Cited

Alderson, Ella. "We're Uncovering One of AI's Deepest Mysteries The black box problem is a secret between machines." Medium. https://medium.com/predict/were-uncovering-one-of-ai-s-deepest-mysteries-27b981ea5ab5. Accessed December 6, 2022.

Anonymous. "7 Ways artificial intelligence can benefit your law firm." American Bar Association. September 2017, https://www.americanbar.org/news/abanews/publications/youraba/2017/september-2017/7-ways-artificial-intelligence-can-benefit-your-law-firm/.

Anonymous. "Generative Adversarial Network." Wikipedia. https://en.wikipedia.org/wiki/Generative_adversarial_network. Accessed October 30, 2022.

Anonymous. "Markov Chain." Wikipedia. https://en.wikipedia.org/wiki/Markov_chain. Accessed October 30, 2022.

Anonymous. "Neural Networks." IBM Cloud Education. 17 August 2020, https://www.ibm.com/cloud/learn/neural-networks.

Anonymous. "Nigram." Wikipedia. https://en.wikipedia.org/wiki/N-gram. Accessed October 30, 2022.

Anonymous. "Overview." OpenAI, https://beta.openai.com/overview. Accessed October 30, 2022.

Anonymous. "ChatGPT: Optimizing, Language Models, for Dialogue." OpenAI. November 30, 2022, https://openai.com/blog/chatgpt/.

Anonymous. "Leveraging AI to advance the power of facts Artificial intelligence at The Associated Press." https://www.ap.org/discover/artificial-intelligence. Accessed October 30, 2022.

Anonymous. "Delivering trusted knowledge with AI." Thomson Reuters. Accessed October 30, 2022, https://www.thomsonreuters.com/en/artificial-intelligence.html.

Anonymous. "Quick Check: Discover a new level of confidence" Tomson Reuters. Accessed October 30, 2022, https://legal.thomsonreuters.com/en/products/westlaw-edge/quick-check?searchid=TRPPCSOL/Google/LegalUS_RS_Westlaw_Quick-Check_Search_Brand-All_US/QuickCheck-All&chl=ppc&cid=9031234&sfdccampaignid=7014O000001BRTBQA4&ef_id=EAIaIQobChMI1fL_wLjq-gIVVMeGCh3mBA5bEAAYASAAEgKwCfD_BwE:G:s&s_kwcid=AL!7944!3!591223841212!p!!g!!westlaw%20edge%20quick%20check.

Anonymous. "Generating Biographies of Marginalized Groups." Meta, March 30, 2022. https://about.fb.com/news/2022/03/generating-biographies-of-marginalized-groups/

Anson, Chris M. "AI-Based Text Generation and the Social Construction of "Fraudulent Authorship": A Revisitation" Composition Studies Chicago Vol. 50, Iss. 1, (Spring 2022): 37-46,179.

Barthes, Roland. "The Death of the Author." Aspen, no. 5-6 in 1967.

Booth, Wayne C. The Rhetoric of Fiction. University of Chicago P. 1961.

Carr, Nicholas. The Shallows: What the Internet Is Doing to Our Brains. W.W. Norton, New York. Updated, 2022.

Cheung, Paul. "Journalism's superfood: AI?" Knight Foundation. November 21, 2019, https://knightfoundation.org/articles/journalisms-superfood-ai/.

Crawford, Kate. Atlas of AI: Power, Politics, and the Planetary Costs of Artificial Intelligence. Yale UP, 2021.

Edwards, Benji. "I'm A Poet And I Know It -- Openai Upgrades Gpt-3, Stunning With Rhyming Poetry And Lyrics" ars Technica. November 2022, https://arstechnica.com/information-technology/2022/11/openai-conquers-rhyming-poetry-with-new-gpt-3-update/.

___. "Galactica language model generated convincing text about fact and nonsense alike." ArsTechnica. November, 18 2022, https://arstechnica.com/information-technology/2022/11/after-controversy-meta-pulls-demo-of-ai-model-that-writes-scientific-papers/.

Foucault, Michel. "What is an Author." Trans. Donald F. Bouchard. Language, Counter-Memory, Practice: Selected Essays and Interviews. Cornell Paperbacks. 1980.

Goody, Jack and Ian Watt. "The Consequences of Literacy." Comparative Studies in Society and History, Volume 5 , Issue 3 , April 1963, pp. 304 - 345.

Griffen, Andrew. "AI deemed 'too dangerous to release' makes it out into the world." Independent. Thursday 07 November 2019, https://www.independent.co.uk/tech/ai-artificial-intelligence-dangerous-text-gpt2-elon-musk-a9192121.html.

Derrida, Jacques, "Plato's Pharmacy" In: Dissemination, translated by Barbara Johnson, Chicago, University of Chicago Press, pp. 63–171: 1981.

Johnson, Jeremy David. "Becoming the Bot: Rhetorical Reflexivity and AI Ethics." Digital Rhetorical Collaborative. APRIL 20, 2018, https://www.digitalrhetoriccollaborative.org/2018/04/20/becoming-the-bot-rhetorical-reflexivity-and-ai-ethics/.

Kent, Thomas. Ed. Post-Process Theory: Beyond The Writing Process Paradigm. SIUP, 1999.

Klingemann, Mario."Another attempt at a longer piece. An imaginary Jerome K. Jerome writes about Twitter." Twitter, https://twitter.com/quasimondo/status/1284509525500989445?lang=en. Accessed 11/15/2022.

Nabokov, Valdimir. Pale Fire. G.P. Putnum's Sons, New York. 1962.

Ong, Walter J. Orality and Literacy: The Technologizing of the Word. Methuen & Co., 1986.

Pistunovich, Natalie "GPT-3 Powers the Next Generation of Apps." https://openai.com/blog/gpt-3-apps/. March 25, 2021.

Plato. Phaedrus. Translated by Alexander Hehamas, Paul Woodruff. Hackett, 1995.

Podolny, Shelley. "If an Algorithm Wrote This, How Would You Even Know?" New York Times March 7, 2015. https://www.nytimes.com/2015/03/08/opinion/sunday/if-an-algorithm-wrote-this-how-would-you-even-know.html. Resnick, Brain. "This psychologist’s “gaydar” research makes us uncomfortable. That’s the point." Vox. January 29, 2018, https://www.vox.com/science-and-health/2018/1/29/16571684/michal-kosinski-artificial-intelligence-faces.

Schmelzer, Ronald. "Definition GPT-3." TechTarget. https://www.techtarget.com/searchenterpriseai/definition/GPT-3. Accessed November 17, 2022.

Shankland, Stephen. "AI Helps the Powerful but Harms the Vulnerable, Mozilla Warns" CNET. July 18, 2022, https://www.cnet.com/tech/computing/ai-helps-the-powerful-but-harms-the-vulnerable-mozilla-warns/.

Tamkin, Alex and Deep Ganguli. "How Large Language Models Will Transform Science, Society, and AI." Stanfor University Human-Centered Artificial Intelligence. Feb 5, 2021, https://hai.stanford.edu/news/how-large-language-models-will-transform-science-society-and-ai.

Turing, Alen. "Computing Machinery and Intelligence." Mind October 1950.

Weiss, Jacob Vaus Eli. "AI Generated Script: How We Made a Movie by an AI Script Writer." builtin. Updated by Hal Koss Ocotober 10, 2022, https://builtin.com/media-gaming/ai-movie-script.

Vigliarolon,Brandon. "Stack Overflow bans ChatGPT as 'substantially harmful' for coding issues." The Register December 5, 2022, https://www.theregister.com/2022/12/05/stack_overflow_bans_chatgpt/.

Wooldridge, Micahel. A Breif History of Artificial Intelligence: What it is, Where We Are, and Where We Are Going.. Flatiron Books, NY: 2021.

Xiang, Chloe. "AI Isn't Artificial or Intelligent " Motherboard: Tech by Vice. December 6, 2022, https://www.vice.com/en/article/wxnaqz/ai-isnt-artificial-or-intelligent

Author Last Name, First Name. "Title of Work. Title of Site, Sponsor or Publisher [include only if different from website title or author], Date of Publication or Update Date, URL. Accessed Date [only if no date of publication or update date].

Writing Engines

AI Writer, $29 month min
Articleforge, $13 month min
Copy, free version
Copysmith
Deepai text generator
EssayAILab, free version
Hyperwrite, free version
Inkforall, free version
Jasper, $40 month min
My Assignment Help
Paper Typer
Rytr, free version
Sassbook, free trial
Smoden, free trial
The Good AI, free trial
Title-Generator
Wordai, 3 day trial
Writesonic, free trial
Writefull
Writer, free trial

Summary Services

Frase
Onai.com
Paraphraser.io
Quillbot summarizer
Scholarcy
Summari.com
Summarizer
TLDRrthis
Wordtune read

Corpus Creation Tools

Sketchengine
Cornell, Text as Data: Finding and Mining: Building your corpus
Building a Wikipedia Text Corpus for Natural Language Processing
Try Expert AI

Corpora

Wiki List of Text Corpora

Articles

“ Is generative AI doomed? An expert’s take on the “model collapse” theory ” 2024 - 10 - 10

Artificial intelligence (AI) prophets and newsmongers are forecasting the end of the generative AI hype, with talk of an impending catastrophic "model collapse".
But how realistic are these predictions? And what is model collapse anyway?
Discussed in 2023, but popularised more recently, "model collapse" refers to a hypothetical scenario where future AI systems get progressively dumber due to the increase of AI-generated data on the internet. >>>

“ The more sophisticated AI models get, the more likely they are to lie ” 2024 - 10 - 10

When a research team led by Amrit Kirpalani, a medical educator at Western University in Ontario, Canada, evaluated ChatGPT’s performance in diagnosing medical cases back in August 2024, one of the things that surprised them was the AI’s propensity to give well-structured, eloquent but blatantly wrong answers. >>>

“ It's Time to Stop Taking Sam Altman at His Word ” 2024 - 10 - 10

OpenAI announced this week that it has raised $6.6 billion in new funding and that the company is now valued at $157 billion overall. This is quite a feat for an organization that reportedly burns through $7 billion a year-far more cash than it brings in-but it makes sense when you realize that OpenAI’s primary product isn’t technology. It’s stories. >>>

“ How ChatGPT Boss Sam Altman’s New AI Predictions Affect Education ” 2024 - 09 - 29

"In his recent blog post, Altman paints a transformative picture of the future with superintelligent AI at its core. As we enter what he terms the "Intelligence Age," the impact on education is imminent.
Altman seems confident in his writing that recent developments are ushering in a era of "unprecedented prosperity and progress." In order to prepare students for success in this new era, we may need to rethink current educational approaches." >>>

“ If your AI seems smarter?, it's thanks to smarter human trainers ” 2024 - 09 - 29

"STOCKHOLM/SAN FRANCISCO, Sept 28 (Reuters) - In the early years, getting AI models like ChatGPT or its rival Cohere to spit out human-like responses required vast teams of low-cost workers helping models distinguish basic facts such as if an image was of a car or a carrot. But more sophisticated updates to AI models in the fiercely competitive arena are now demanding a rapidly expanding network of human trainers who have specialized knowledge -- from historians to scientists, some with doctorate degrees.
"A year ago, we could get away with hiring undergraduates, to just generally teach AI on how to improve," said Cohere co-founder Ivan Zhang, talking about its internal human trainers.
"Now we have licensed physicians teaching the models how to behave in medical environments, or financial analysts or accountants."" >>>

“ OpenAI was a research lab — now it’s just another tech company ” 2024 - 09 - 28

"OpenAI launched with a famously altruistic mission: to help humanity by developing artificial general intelligence. But along the way, it became one of the best-funded companies in Silicon Valley. Now, the tension between those two facts is coming to a head.
Weeks after releasing a new model it claims can "reason," OpenAI is barreling toward dropping its nonprofit status, some of its most senior employees are leaving, and CEO Sam Altman -- who was once briefly ousted over apparent trust concerns -- is solidifying his position as one of the most powerful people in tech." >>>

“ Nvidia's Jensen Huang sees possibilities in AI power use ” 2024 - 09 - 28

"Nvidia CEO Jensen Huang contends that AI's benefits for the power grid and society ultimately will offset its massive energy suck.
Why it matters: AI's rise is fueling fears in the power sector and the climate community about grid reliability and meeting greenhouse gas emissions reduction targets." >>>

“ OpenAI Is Growing Fast and Burning Through Piles of Money ” 2024 - 09 - 28

"As the company looks for more outside investors, documents reviewed by The New York Times show consumer fascination with ChatGPT and a serious need for more cash. ... OpenAI, the San Francisco start-up behind ChatGPT, has been telling investors that it is making billions from its chatbot and that it expects to make a lot more in the coming years. But it has not been quite so clear about how much it is losing." >>>

“ ‘We nicknamed it Eddy’: what do schools and teachers think of AI in classrooms? ” 2024 - 09 - 28

"ChatGPT has been met with both anxiety and a sense of optimism. While there has been a lot of discussion about what is happening in universities, there has been less attention given to schools.
We have been looking at trials of AI in schools in South Australia. Here’s what we found." >>>

“ Clones in the classroom: why universities must be wary of embracing AI-driven teaching tools ” 2024 - 09 - 28

"The university sector in Aotearoa New Zealand is at a tipping point due to chronic underfunding, shifting enrolments and increasing costs from inflation. In response, the government has established two working groups to assess the health of the sector and provide recommendations for the future.
Meanwhile, universities find themselves increasingly beholden to the education technology (EdTech) industry, which claims to improve student learning by selling hardware and software - often built with artificial intelligence (AI)." >>>

“ The Future of Writing Is a Lot Like Hip-Hop ” 2024 - 09 - 28

"A new kind of literary curation will be the defining skill for the next era of human creativity." >>>

“ Meta is working on recreating influencers with AI ” 2024 - 09 - 28

"Meta has big ambitions for using AI to help creators, and it showed two impressive demos of what that could look like onstage at Connect today." >>>

“ Microsoft deal propels Three Mile Island restart, with key permits still needed ” 2024 - 09 - 28

"Big tech has led to a sudden surge in U.S. electricity demand for data centers needed to expand technologies like artificial intelligence and cloud computing. Nuclear energy, which is nearly carbon-free and broadly considered more reliable than energy sources like solar and wind, has become a popular option for technology companies with uninterrupted power needs and climate pledges.
'Nuclear plants are the only energy sources that can consistently deliver on that promise,' Constellation Chief Executive Officer Joe Dominguez said in a statement. " >>>

“ ChatGPT is changing the way we write. Here’s how -- and why it’s a problem ” 2024 - 09 - 28

"Have you noticed certain words and phrases popping up everywhere lately?
Phrases such as "delve into" and "navigate the landscape" seem to feature in everything from social media posts to news articles and academic publications. They may sound fancy, but their overuse can make a text feel monotonous and repetitive." >>>

“ AI Datacenters More Than 600 Percent Worse for Environment Than Tech Companies Claimed ” 2024 - 09 - 28

"If these companies were one country, their actual emissions would rank them as the 33rd biggest emitter in the world." >>>

“ We Must Approach AI Like the Automobile ” 2024 - 09 - 28

"In the near future, I want you to learn how to ride this new horse of artificial intelligence (AI) rather than be left behind with the old one. Let me explain the revolutionary changes approaching our lives. " [Pullman would add that the car also transformed landscapes -- highways and suburbs -- and helped foster racism, classism, and colonialism] >>>

“ AI is 'accelerating the climate crisis,' expert warns ” 2024 - 09 - 28

"If you care about the environment, think twice about using AI. Generative artificial intelligence uses 30 times more energy than a traditional search engine, warns researcher Sasha Luccioni, on a mission to raise awareness about the environmental impact of the hot new technology." >>>

“ New paper explores the blurred lines between AI and human communication ” 2024 - 09 - 28

"Artificial intelligence (AI) is becoming increasingly sophisticated. In a thought-provoking paper published in Phenomenology and the Cognitive Sciences, Thomas Fuchs argues that true understanding and empathy require the subjectivity that is inherent to living beings, cautioning against the blurring lines between real and simulated interactions.
A robot may be able to engage in conversation that mirrors one's emotions and respond with uncanny human-like behavior, but it's just that-it's almost natural." >>>

“ OpenAI releases o1, its first model with ‘reasoning’ abilities ” 2024 - 09 - 26

"OpenAI is releasing a new model called o1, the first in a planned series of "reasoning" models that have been trained to answer more complex questions, faster than a human can. It's being released alongside o1-mini, a smaller, cheaper version. " >>>

“ OpenAI Executives Exit as C.E.O. Works to Make the Company For-Profit ” 2024 - 09 - 26

"Mira Murati, the chief technology officer, and two others are leaving as leaders including Sam Altman work to transform the start-up." >>>

“ Microsoft claims its AI safety tool not only finds errors but also fixes them ” 2024 - 09 - 26

"Microsoft is launching a new feature called "correction" that builds on the company's efforts to combat AI inaccuracies. Customers using Microsoft Azure to power their AI systems can now use the capability to automatically detect and rewrite incorrect content in AI outputs." >>>

“ Hacker plants false memories in ChatGPT to steal user data in perpetuity ” 2024 - 09 - 26

"Emails, documents, and other untrusted content can plant malicious memories." >>>

“ That Message From Your Doctor? It May Have Been Drafted by A.I. ” 2024 - 09 - 26

"Overwhelmed by queries, physicians are turning to artificial intelligence to correspond with patients. Many have no clue that the replies are software-generated." >>>

“ They think they’re building God ” 2024 - 09 - 26

"OpenAI's new model, called o1, appears to think and ponder as you use it. But is it thinking? Or pondering? And what does it mean if it is? Would that make it worth the risks, which appear to be both greater and more plausible than ever? How do you balance the risks of destroying humanity with the possibility of improving it? This is the thing about talking about artificial intelligence: it has this nasty penchant of getting all existential on you." >>>

“ Will A.I. Be a Bust? A Wall Street Skeptic Rings the Alarm ” 2024 - 09 - 24

"Jim Covello, Goldman Sachs's head of stock research, warned that building too much of what the world doesn't need "typically ends badly."" >>>

“ The chatbot becomes the teacher ” 2024 - 09 - 24

"On The Vergecast: Steven Johnson tells us about NotebookLM, the AI-assisted future of learning, and how to teach an AI bot to tell the truth." >>>

“ I tried Google’s new one-click AI podcast creator, and now I don’t know what’s real anymore ” 2024 - 09 - 24

"I've had a glimpse of how AI will change the world, and it’s filling me with both fear and wonder in equal measure.
The source of my consternation is Google NotebookLM. NotebookLM takes an article, blog post, or web page, and with just one click produces an audio file of a conversation between two people about it that sounds so natural and realistic that there is no way you’d believe you weren't listening to two real people talking." >>>

“ Microsoft needs so much power for AI that Three Mile Island is reopening ” 2024 - 09 - 24

>>>

“ AI Datacenters More Than 600 Percent Worse for Environment Than Tech Companies Claimed ” 2024 - 09 - 24

"What tech companies have claimed so far about the energy costs of building enormous AI models may have been incredibly misleading. Or, depending on your perspective, they lied to you.
The Guardian reports that the actual emissions made by data centers owned by AI leaders including Microsoft, Google, Meta, and Apple, are about 662 percent higher than what they've officially reported." >>>

“ Why OpenAI’s new model is such a big deal ” 2024 - 09 - 19

"Unlike previous models that are well suited for language tasks like writing and editing, OpenAI o1 is focused on multistep "reasoning," the type of process required for advanced mathematics, coding, or other STEM-based questions. It uses a "chain of thought" technique, according to OpenAI. "It learns to recognize and correct its mistakes. It learns to break down tricky steps into simpler ones. It learns to try a different approach when the current one isn't working," the company wrote in a blog post on its website." >>>

“ OpenAI says the latest ChatGPT can ‘think’ – and I have thoughts ” 2024 - 09 - 19

"We are still largely in the dark about how these things work-and "we" includes the developers of such tools. OpenAI has said this ability to reason is a big thing - the company has even trotted out a questionable claim that o1 is its most dangerous model yet (see here for how that's sometimes more marketing spiel than anything). Those who have tried probing the limits of the o1 model seem to agree with their point about the reasoning, but less so with the danger part." >>>

“ IBM will train you in AI fundamentals for free, and give you a skill credential - in 10 hours ” 2024 - 09 - 12

>>>

“ Taylor Swift and the Power of the AI Backlash ” 2024 - 09 - 12

..."The thing about the false endorsement to which she's responding, though, is that it probably didn't need to be refuted. " >>>

“ Why Students Should Resist Using ChatGPT ” 2024 - 09 - 12

"Students should avoid ChatGPT because learning to write is learning to think." >>>

“ Put levy on smartphones to help creatives survive AI threat, top UK artists tell Labour ” 2024 - 09 - 12

"More than 4,000 artists have called on the government to create a levy on smartphone sales to fund ­visual art in the face of cuts, studio closures and the rise of generative AI." >>>

“ If journalism is going up in smoke, I might as well get high off the fumes’: confessions of a chatbot helper ” 2024 - 09 - 12

"For several hours a week, I write for a technology company worth billions of dollars. Alongside me are published novelists, rising academics and several other freelance journalists. The workload is flexible, the pay better than we are used to, and the assignments never run out. But what we write will never be read by anyone outside the company.
That's because we aren't even writing for people. We are writing for an AI." >>>

“ The Challenge Is to Write 50,000 Words in a Month. Should ChatGPT Be Able to Help? ” 2024 - 09 - 12

"An online writing community was set aflame this week after National Novel Writing Month, or NaNoWriMo, said it wouldn’t take a stance on the use of A.I." >>>

“ A third of all generative AI projects will be abandoned, says Gartner ” 2024 - 09 - 12

"Companies are "struggling" to find value in the generative artificial intelligence (Gen AI) projects they have undertaken and one-third of initiatives will end up getting abandoned, according to a recent report by analyst Gartner." >>>

“ What is ‘model collapse’? An expert explains the rumours about an impending AI doom ” 2024 - 09 - 12

"Artificial intelligence (AI) prophets and newsmongers are forecasting the end of the generative AI hype, with talk of an impending catastrophic "model collapse".
But how realistic are these predictions? And what is model collapse anyway?
Discussed in 2023, but popularised more recently, "model collapse" refers to a hypothetical scenario where future AI systems get progressively dumber due to the increase of AI-generated data on the internet." >>>

“ AI Cheating Is Getting Worse: Colleges still don’t have a plan. ” 2024 - 09 - 12

"A mere week after ChatGPT appeared in November 2022, The Atlantic declared that "The College Essay Is Dead." Two school years later, Jensen is done with mourning and ready to move on. The tall, affable English professor co-runs a National Endowment for the Humanities-funded project on generative-AI literacy for humanities instructors, and he has been incorporating large language models into ASU's English courses. Jensen is one of a new breed of faculty who want to embrace generative AI even as they also seek to control its temptations. He believes strongly in the value of traditional writing but also in the potential of AI to facilitate education in a new way-in ASU's case, one that improves access to higher education." >>>

“ AI May Not Steal Many Jobs After All. It May Just Make Workers More Efficient ” 2024 - 09 - 03

"The experience at Alorica — and at other companies, including furniture retailer IKEA — suggests that AI may not prove to be the job killer that many people fear. Instead, the technology might turn out to be more like breakthroughs of the past — the steam engine, electricity, the Internet: That is, eliminate some jobs while creating others. And probably making workers more productive in general, to the eventual benefit of themselves, their employers and the economy." >>>

“ Kids Who Use ChatGPT as a Study Assistant Do Worse on Tests ” 2024 - 09 - 03

"A third group of students had access to a revised version of ChatGPT that functioned more like a tutor. This chatbot was programmed to provide hints without directly divulging the answer. The students who used it did spectacularly better on the practice problems, solving 127% more of them correctly compared with students who did their practice work without any high-tech aids. But on a test afterwards, these AI-tutored students did no better. Students who just did their practice problems the old fashioned way --on their own — matched their test scores." >>>

“ What’s the Future for Software Developers? ” 2024 - 08 - 31

"Make no mistake: she still thinks understanding how to write software is a useful skill. But learning how to think about problems and ask the right questions might be better preparation for a tech career in the future, Bailey suggested: "It's becoming much, much more a scenario where this magic is kind of happening in the margins between computer science and some other disciplines."" >>>

“ California legislature passes sweeping AI safety bill ” 2024 - 08 - 31

" "The bill, which has been a flashpoint for debate in Silicon Valley and beyond, would obligate AI companies operating in California to implement a number of precautions before they train a sophisticated foundation model. Those include making it possible to quickly and fully shut the model down, ensuring the model is protected against "unsafe post-training modifications," and maintaining a testing procedure to evaluate whether a model or its derivatives is especially at risk of “causing or enabling a critical harm." " >>>

“ Can You Tell Which Short Story ChatGPT Wrote? ” 2024 - 08 - 31

"Listen as Ms. Sittenfeld sits down with the Opinion editor Susannah Meadows to talk about what they learned after pitting her writing against artificial intelligence, and hear excerpts from both stories to decide for yourself which is the more compelling read." >>>

“ How AI Is Deciphering Lost Scrolls From the Roman Empire ” 2024 - 08 - 31

"Researchers are using cutting-edge AI models to "read" ancient scrolls superheated by the eruption of Mount Vesuvius in 79, which covered much of the Bay of Naples in ash--including the now-famous towns of Pompeii and Herculaneum. Though the work to decode the scrolls began centuries before the artificial intelligence revolution emerged, myriad new technologies are making that work easier and faster than ever before." >>>

“ Cursor is ChatGPT for coding -- now anyone can make an app in minutes ” 2024 - 08 - 31

"Cursor is part development environment, part AI chatbot and unlike tools like GitHub Copilot it can more or less do all of the work for you, transforming a simple idea into functional code in minutes." >>>

“ Anthropic publishes the ‘system prompts’ that make Claude tick ” 2024 - 08 - 31

Generative AI models aren't actually humanlike. They have no intelligence or personality -- they're simply statistical systems predicting the likeliest next words in a sentence. But like interns at a tyrannical workplace, they do follow instructions without complaint -- including initial "system prompts" that prime the models with their basic qualities and what they should and shouldn't do.
Every generative AI vendor, from OpenAI to Anthropic, uses system prompts to prevent (or at least try to prevent) models from behaving badly, and to steer the general tone and sentiment of the models' replies. For instance, a prompt might tell a model it should be polite but never apologetic, or to be honest about the fact that it can’t know everything. >>>

“ Why Artificial Intelligence Hype Isn't Living Up To Expectations ” 2024 - 08 - 31

"Fast forward almost two years and we must ask—has AI lived up to expectations?
According to a report by the U.S. Census Bureau, there are some indications that AI may not be the game-changer it was promised to be. Let's explore five key takeaways from the report and what leaders like you can do to be more strategic about AI adoption." >>>

“ AI in the Writing Classroom: Professor, Beware ” 2024 - 08 - 31

Generative artificial intelligence has no role in the walled garden of teaching a student how to write. >>>

“ Improve Your Writing With ChatGPT (5 Powerful Prompts) ” 2024 - 08 - 31

"There's no better way to build an audience than writing online. Creating the habit of showing up and hitting publish will serve you well for everything in your professional future. But there’s a wrong way to produce. Without studying the data and learning how to improve, your words won't hit the mark. Don't get stale. Don't let people switch off. Take your online writing to a whole new level and be forever proud of everything you share." >>>

“ No laughing matter - how AI is helping comedians write jokes ” 2024 - 08 - 15

"Comedians are increasingly experimenting with the technology to write scripts and brainstorm ideas, including Anesti Danelis. Earlier this year, the Canadian asked popular AI chatbot ChatGPT to write him a show." >>>

“ On Whether Generative AI And Large Language Models Are Better At Inductive Reasoning Or Deductive Reasoning And What This Foretells About The Future Of AI ” 2024 - 08 - 15

"In today's column, I continue my ongoing analysis of the latest advances and breakthroughs in AI, see my extensive posted coverage at the link here, and focus in this discussion on the challenges associated with various forms of reasoning that are mathematically and computationally undertaken via modern-day generative AI and large language models (LLM). Specifically, I will do a deep dive into inductive reasoning and deductive reasoning." >>>

“ Copyright group takes down Dutch language AI dataset ” 2024 - 08 - 15

AMSTERDAM, Aug 13 (Reuters) - Dutch-based copyright enforcement group BREIN has taken down a large language dataset that was being offered for use in training AI models, the organization said on Tuesday.
The dataset included information collected without permission from tens of thousands of books, news sites, and Dutch language subtitles harvested from "countless" films and TV series, BREIN said in a statement. >>>

“ An empirical investigation of the impact of ChatGPT on creativity ” 2024 - 08 - 15

"This paper investigates the potential of ChatGPT for helping humans tackle problems that require creativity. Across five experiments, we asked participants to use ChatGPT (GPT-3.5) to generate creative ideas for various everyday and innovation-related problems, including choosing a creative gift for a teenager, making a toy, repurposing unused items and designing an innovative dining table. We found that using ChatGPT increased the creativity of the generated ideas compared with not using any technology or using a conventional Web search (Google). This effect remained robust regardless of whether the problem required consideration of many (versus few) constraints and whether it was viewed as requiring empathetic concern. Furthermore, ChatGPT was most effective at generating incrementally (versus radically) new ideas. Process evidence suggests that the positive influence of ChatGPT can be attributed to its capability to combine remotely related concepts into a cohesive form, leading to a more articulate presentation of ideas." >>>

“ OpenAI Has Software That Detects AI Writing With 99.9 Percent Accuracy, Refuses to Release It ” 2024 - 08 - 15

ChatGPT creator OpenAI has developed internal tools for watermarking and tracking AI-generated content with 99.9 percent accuracy, the Wall Street Journal reports — but is refusing to release it.
Effective tools for flagging AI-generated text could be useful in any number of situations, from cracking down on cheating students to sorting through the AI-generated sludge filling the web. >>>

“ Flood of 'junk': How AI is changing scientific publishing ” 2024 - 08 - 11

"An infographic of a rat with a preposterously large penis. Another showing human legs with way too many bones. An introduction that starts: "Certainly, here is a possible introduction for your topic".
These are a few of the most egregious examples of artificial intelligence that have recently made their way into scientific journals, shining a light on the wave of AI-generated text and images washing over the academic publishing industry." >>>

“ Meet Prompt Poet: The Google-acquired tool revolutionizing LLM prompt engineering ” 2024 - 08 - 11

"In the age of artificial intelligence, prompt engineering is an important new skill for harnessing the full potential of large language models (LLMs). This is the art of crafting complex inputs to extract relevant, useful outputs from AI models like ChatGPT. While many LLMs are designed to be friendly to non-technical users, and respond well to natural-sounding conversational prompts, advanced prompt engineering techniques offer another powerful level of control. These techniques are useful for individual users, and absolutely essential for developers seeking to build sophisticated AI-powered applications....Prompt Poet potentially offers a look at the future direction of prompt context management across Google’s AI projects, such as Gemini." >>>

“ Are we prepared for ‘Act 2’ of gen AI? ” 2024 - 08 - 05

We are only in what I'd call "Act 1" of the gen AI story. Previously unimaginable amounts of data and compute have created models that demonstrate (a key word) what gen AI can deliver. However, these early experiments have also brought compromises, exceptions, cost concerns and, yes, errors. After all, fast-evolving technologies are inherently fragile at the start.
However, we must ensure we don't remain mired in Act 1. Much more work remains on the pragmatics of operationalizing gen AI. This work -- what I'd call "Act 2" -- may be less glamourous, but it is no less essential to the success of this technology. >>>

“ Google pulls its terrible pro-AI “Dear Sydney” ad after backlash ” 2024 - 08 - 05

"... Not only is AI coming for human creativity, the "Dear Sydney" ad suggests—but it won't even leave space for the charming imperfections of a child's fan letter to an athlete. Instead, AI will provide the template, just as it will likely provide the template for the athlete's response, leading to a nightmare scenario in which huge swathes of human communication have the "human" part stripped right out...." >>>

“ Writer’s new AI models are scary good at healthcare and finance tasks ” 2024 - 08 - 05

"San Francisco-based AI company Writer launched two specialized large language models (LLMs) tailored specifically for the healthcare and financial services industries on Wednesday, potentially reshaping how these highly regulated sectors adopt artificial intelligence." >>>

“ Knowing About Temperature Settings When Using Generative AI Is Hot Stuff For Prompt Engineering ” 2024 - 08 - 05

"In today's column, I am continuing my ongoing coverage of prompt engineering strategies and tactics that aid in getting the most out of using generative AI apps such as ChatGPT, GPT-4, Bard, Gemini, Claude, etc. The focus this time will be on the importance of a technical aspect known as "temperature" and "temperature settings" which involve important parameter adjustments that can be made in some generative AI apps." >>>

“ From sci-fi to state law: California’s plan to prevent AI catastrophe ” 2024 - 07 - 30

"California's "Safe and Secure Innovation for Frontier Artificial Intelligence Models Act" (a.k.a. SB-1047) has led to a flurry of headlines and debate concerning the overall "safety" of large artificial intelligence models. But critics are concerned that the bill's overblown focus on existential threats by future AI models could severely limit research and development for more prosaic, non-threatening AI uses today." >>>

“ New paper explores the blurred lines between AI and human communication ” 2024 - 07 - 28

Artificial intelligence (AI) is becoming increasingly sophisticated. In a thought-provoking paper published in Phenomenology and the Cognitive Sciences, Thomas Fuchs argues that true understanding and empathy require the subjectivity that is inherent to living beings, cautioning against the blurring lines between real and simulated interactions.
A robot may be able to engage in conversation that mirrors one's emotions and respond with uncanny human-like behavior, but it's just that–it's almost natural. >>>

“ Scientists are trying to unravel the mystery behind modern AI ” 2024 - 07 - 27

"It's like studying the brain: really, really hard. They're doing it anyway." >>>

“ OpenAI Will Reportedly Announce An AI-Powered Search Engine Next Week — Here’s What We Know ” 2024 - 07 - 27

" OpenAI will reportedly announce an artificial intelligence-powered search engine for its flagship chatbot ChatGPT on Monday, a much hyped and speculated feature that would ratchet up competition with search giant Google as startups and Big Tech alike race to cash in on the tech world’s latest gold rush." >>>

“ Forget coding bootcamps: Airtable’s AI can build your app in seconds ” 2024 - 07 - 27

Airtable, the $11 billion no-code platform unicorn, has unveiled Cobuilder, an AI-powered tool that generates customizable applications in seconds using natural language prompts. This launch could reshape the landscape of enterprise software development by allowing non-technical employees to build complex applications without coding knowledge. >>>

“ Move Over, Mathematicians, Here Comes AlphaProof ” 2024 - 07 - 27

"A.I. is getting good at math -- and might soon make a worthy collaborator for humans." >>>

“ AI’s Real Hallucination Problem ” 2024 - 07 - 27

"Tech executives are acting like they own the world." >>>

“ Chinese companies offer to 'resurrect' dead loved ones. It raises questions ” 2024 - 07 - 27

>>>

“ “Copyright traps” could tell writers if an AI has scraped their work ” 2024 - 07 - 27

The technique has been used throughout history, but now could be a tool in one of the biggest fights in artificial intelligence. >>>

“ Search as we know it is officially over ” 2024 - 07 - 27

"Google is dying. Google is unstoppable. Somehow, right now, it feels like both of those things are true. For the first time in more than a decade, there appear to be products that might actually threaten Google Search as the centerpiece of the web - including OpenAI's new SearchGPT. And yet Google Search continues to dominate the market and make truly unfathomable amounts of money. >>>

“ Robots sacked, screenings shut down: a new movement of luddites is rising up against AI ” 2024 - 07 - 27

"Earlier this month, a popular lifestyle magazine introduced a new "fashion and lifestyle editor" to its huge social media following. "Reem", who on first glance looked like a twentysomething woman who understood both fashion and lifestyle, was proudly announced as an "AI enhanced team member". That is, a fake person, generated by artificial intelligence. Reem would be making product recommendations to SheerLuxe’s followers - or, to put it another way, doing what SheerLuxe would otherwise pay a person to do. The reaction was entirely predictable: outrage, followed by a hastily issued apology. One suspects Reem may not become a staple of its editorial team." >>>

“ The Push to Develop Generative A.I. Without All the Lawsuits ” 2024 - 07 - 20

"Companies like Getty have begun developing A.I. models with their own data, part of a broader push to build artificial intelligence with licensed content." >>>

“ How ChatGPT is Changing the Face of Programming ” 2024 - 07 - 20

Since the launch of OpenAI's ChatGPT, the programming landscape has entered a new era. By leveraging advanced natural language processing capabilities, beginners and experienced developers now have powerful tools to ease the coding process.
AI-powered chatbots like ChatGPT or Gemini transform how developers solve complex problems and learn new technologies. This is why, when OpenAI was first released GPT-4, many users tested its ability to create functional programs from scratch.
The result? >>>

“ AI prompts can boost writers’ creativity but result in similar stories, study finds ” 2024 - 07 - 14

"A study suggests that ideas generated by the AI system ChatGPT can help boost the creativity of writers who lack inherent flair – albeit at the expense of variety.
Prof Oliver Hauser, a co-author of the research from the University of Exeter, said the results pose a social dilemma." >>>

“ Opinion: What’s behind the AI boom? Exploited humans ” 2024 - 07 - 14

"Today we are in the middle of a hype cycle in which companies are racing to integrate artificial intelligence tools into products, transforming fields including logistics, manufacturing and healthcare. The global AI market was worth approximately $200 billion in 2023 and is expected to grow more than 20% each year to nearly $2 trillion by 2030. There are no exact numbers of how many workers participate globally in the industry, but the figure is in the millions. And if trends continue at their current rate, their number will expand dramatically." >>>

“ MIT researchers introduce generative AI for databases ” 2024 - 07 - 14

"This new tool offers an easier way for people to analyze complex tabular data." >>>

“ Research shows AI can boost creativity for some, but at a cost ” 2024 - 07 - 14

Supporters of artificial intelligence say it can serve as a muse, but critics doubt it -- they say that it does little more than remix existing work.
Now, new research suggests that elements of both arguments are right. AI might be able to help a person become more creative, but it risks decreasing creativity in society overall. >>>

“ Two 80-something journalists tried ChatGPT. Then, they sued to protect the ‘written word’ ” 2024 - 07 - 14

>>>

“ AI brings soaring emissions for Google and Microsoft, a major contributor to climate change ” 2024 - 07 - 14

"Researcher Jesse Dodge did some back-of-the-napkin math on the amount of energy AI chatbots use.
"One query to ChatGPT uses approximately as much electricity as could light one light bulb for about 20 minutes," he says. "So, you can imagine with millions of people using something like that every day, that adds up to a really large amount of electricity." " >>>

“ Defeated by A.I., a Legend in the Board Game Go Warns: Get Ready for What’s Next ” 2024 - 07 - 14

"Lee Saedol was one of the world's top Go players, and his shocking loss to an A.I. opponent was a harbinger of a new, unsettling era. "It may not be a happy ending," he says." >>>

“ Anthropic’s Claude adds a prompt playground to quickly improve your AI apps ” 2024 - 07 - 14

Prompt engineering became a hot job last year in the AI industry, but it seems Anthropic is now developing tools to at least partially automate it.
Anthropic released several new features on Tuesday to help developers create more useful applications with the startup’s language model, Claude, according to a company blog post. Developers can now use Claude 3.5 Sonnet to generate, test and evaluate prompts, using prompt engineering techniques to create better inputs and improve Claude's answers for specialized tasks. >>>

“ 'Pulpit AI' aims to help pastors use artificial intelligence to preach beyond Sunday services ” 2024 - 07 - 14

A new artificial intelligence platform aimed at helping pastors preach their sermons more effectively is set to launch later this month.
Pulpit AI, created by Michael Whittle and Jake Sweetman, will be released officially on July 22 and will include both free and paid versions, according to both men. >>>

“ Mind-reading AI turns thoughts into pictures with unprecedented accuracy ” 2024 - 07 - 14

"This special AI learned which parts of the brain to focus on, making the pictures it created even more accurate." >>>

“ AI outshines humans in humor: Study finds ChatGPT is as funny as The Onion ” 2024 - 07 - 14

"Artificial intelligence has been making headlines for its capabilities in various fields, but can it make us laugh? A recent study published in the journal PLOS ONE suggests that AI might have the upper hand in humor as well. The research shows that AI-generated humor was rated as equally funny or funnier than human-created jokes, even when pitted against professional satirists from The Onion." >>>

“ Google’s emissions climb nearly 50% in five years due to AI energy demand ” 2024 - 07 - 04

"Google's goal of reducing its climate footprint is in jeopardy as it relies on more and more energy-hungry data centres to power its new artificial intelligence products. The tech giant revealed Tuesday that its greenhouse gas emissions have climbed 48% over the past five years." >>>

“ Researchers made an algorithm that can tell when AI is hallucinating ” 2024 - 06 - 25

>>>

“ The Chef Is Human. The Reviewer Isn’t. ” 2024 - 06 - 25

"A new study showed people real restaurant reviews and ones produced by A.I. They couldn't tell the difference." >>>

“ Ahead of GPT-5 launch, another test shows that people cannot distinguish ChatGPT from a human in a conversation test -- is it a watershed moment for AI? ” 2024 - 06 - 25

"Popular AI tools such as GPT-4 generate fluent, human-like text and perform so well on various language tasks it's becoming increasingly difficult to tell if the person you're conversing with is human or a machine. " >>>

“ AI is an energy hog. This is what it means for climate change. ” 2024 - 06 - 24

"So how worried should we be about AI's electricity demands? Well, it's complicated. " >>>

“ Big Tech's massive AI power demand is driving up this energy stock ” 2024 - 06 - 20

>>>

“ AIs are coming for social networks ” 2024 - 06 - 20

"So far, generative AI has been mostly confined to chatbots like ChatGPT. Startups like Character.AI and Replika are seeing early traction by making chatbots more like companions. But what happens when you dump a bunch of AI characters into something that looks like Instagram and let them talk to each other?
That's the idea behind Butterflies, one of the most provocative -- and, at times, unsettling -- takes on social media that I've seen in quite a while." >>>

“ AI TOOLS CAUSE A DECLINE IN FREELANCER WORK AND INCOME – AT LEAST IN THE SHORT RUN ” 2024 - 06 - 19

"Olin researchers Oren Reshef and Xiang Hui (along with a colleague from New York University, Luofeng Zhou) set out to quantify how AI tools have affected specific subsets of the labor market—writing-related and image-related freelance workers.
"There's a lot of uncertainty trying to predict what the effects of AI will be in 10 years, but AI could be very different in 10 years," said Reshef, an assistant professor of strategy. "We were thinking, 'Let's try to see empirically what the direct effect is in the very short run.'" >>>

“ Become UNSTOPPABLE with data Become UNSTOPPABLE with data 5 Machine Learning Models Explained in 5 Minutes ” 2024 - 06 - 07

"Learn about the most popular machine learning models, understand how they work, and discover the best free courses to master them." >>>

“ This Is What It Looks Like When AI Eats the World ” 2024 - 06 - 07

"The web itself is being shoved into a great unknown." >>>

“ ChatGPT is now better than ever at faking human emotion and behavior ” 2024 - 06 - 07

Studies show users are more likely to trust and cooperate with chatbots exhibiting social intelligence and personality traits. This could prove relevant in fields such as education, where studies have indicated AI chatbots can boost learning outcomes and motivation.
However, some commentators worry users may become overly attached to AI systems with human-like personalities or emotionally harmed by the one-way nature of human-computer interaction. >>>

“ Stability AI releases a sound generator ” 2024 - 06 - 07

"Called Stable Audio Open, the generative model takes a text description (e.g., "Rock beat played in a treated studio, session drumming on an acoustic kit") and outputs a recording up to 47 seconds in length. The model was trained using around 486,000 samples from free music libraries Freesound and the Free Music Archive." >>>

“ Current and former OpenAI employees warn of AI’s ‘serious risks’ and lack of oversight ” 2024 - 06 - 07

"Current and former OpenAI employees published an open letter describing concerns about the artificial intelligence industry's rapid advancement despite a lack of oversight and a lack of whistleblower protections.
"AI companies have strong financial incentives to avoid effective oversight," the employees wrote.
OpenAI, Google, Microsoft and other companies are at the helm of a generative AI arms race -- a market that is predicted to top $1 trillion in revenue within a decade." >>>

“ What We Learned from a Year of Building with LLMs (Part I) ” 2024 - 06 - 03

"While the barrier to entry for building AI products has been lowered, creating those effective beyond a demo remains a deceptively difficult endeavor.
We've identified some crucial, yet often neglected, lessons and methodologies informed by machine learning that are essential for developing products based on LLMs. Awareness of these concepts can give you a competitive advantage against most others in the field without requiring ML expertise! " >>>

“ WTF is AI? ” 2024 - 06 - 03

"So what is AI, anyway? The best way to think of artificial intelligence is as software that approximates human thinking. It's not the same, nor is it better or worse, but even a rough copy of the way a person thinks can be useful for getting things done. Just don’t mistake it for actual intelligence!" >>>

“ Google's AI Overviews Will Always Be Broken. That's How AI Works ” 2024 - 06 - 03

"The current AI boom is built around LLMs' impressive fluency with text, but the software can also use that facility to put a convincing gloss on untruths or errors. Using the technology to summarize online information promises can make search results easier to digest, but it is hazardous when online sources are contractionary or when people may use the information to make important decisions." >>>

“ Journalists “deeply troubled” by OpenAI’s content deals with Vox, The Atlantic ” 2024 - 06 - 03

"On Wednesday, Axios broke the news that OpenAI had signed deals with The Atlantic and Vox Media that will allow the ChatGPT maker to license their editorial content to further train its language models. But some of the publications' writers--and the unions that represent them--were surprised by the announcements and aren't happy about it. Already, two unions have released statements expressing "alarm" and "concern."" >>>

“ 20 Novel Ways To Improve Your ChatGPT Prompts (According To Science) ” 2024 - 06 - 03

According to OpenAI cofounder Sam Altman, ChatGPT has 100 million weekly users. Many of these are founders using the friendly (and now all-knowing) chatbot to supercharge their personal brand, adopt a winner's mindset, and outperform their competitors. But how do you know you're using the tool as effectively as possible? You're probably not. These unconventional pointers will ensure you're not missing out on that top tier of results. >>>

“ The New ChatGPT Offers a Lesson in A.I. Hype ” 2024 - 06 - 03

"When OpenAI unveiled the latest version of its immensely popular ChatGPT chatbot this month, it had a new voice possessing humanlike inflections and emotions. The online demonstration also featured the bot tutoring a child on solving a geometry problem.
To my chagrin, the demo turned out to be essentially a bait and switch. " >>>

“ A Short History Of ChatGPT: How We Got To Where We Are Today ” 2024 - 05 - 30

"Picture an AI that truly speaks your language -- and not just your words and syntax. Imagine an AI that understands context, nuance, and even humor.
This is no longer just a futuristic concept --it's the reality of ChatGPT." >>>

“ If A.I. Can Do Your Job, Maybe It Can Also Replace Your C.E.O. ” 2024 - 05 - 29

"Chief executives are vulnerable to the same forces buffeting their employees. Leadership is important, but so is efficiency — and cost-cutting." >>>

“ An Alternative to Conventional Neural Networks Could Help Reveal What AI Is Doing behind the Scenes ” 2024 - 05 - 29

"Despite their performance, current AI models have major weaknesses: they require enormous resources and are indecipherable. Help may be on the way." >>>

“ Scarlett Johansson’s OpenAI clash is just the start of legal wrangles over artificial intelligence ” 2024 - 05 - 29

"When OpenAI's new voice assistant said it was "doing fantastic" in a launch demo this month, Scarlett Johansson was not.
The Hollywood star said she was "shocked, angered and in disbelief" that the updated version of ChatGPT, which can listen to spoken prompts and respond verbally, had a voice "eerily similar" to hers." >>>

“ Imagine how great universities could be without all those human teachers ” 2024 - 05 - 25

"This is the third in The Vanishing University, a four-part series exploring the tech-driven future of higher education in America. Here are parts one, two, and four." [published in 2017, 5 years before OpenAI's Hello world moment] >>>

“ My A.I. Writing Robot ” 2024 - 05 - 25

"A new wave of artificial-intelligence startups is trying to "scale language" by automating the work of writing. I asked one such company to try to replace me." >>>

“ Gig workers are writing essays for AI to learn from ” 2024 - 05 - 25

"Companies are hiring highly educated gig workers to write training content for AI models.
The shift toward more sophisticated trainers comes as tech giants scramble for new data sources.
AI could run out of data to learn from by 2026, one research institute has warned. " >>>

“ The Impact of AI on Writing and Writing Instruction ” 2024 - 05 - 25

Jim Porter published this in 2018. >>>

“ New Anthropic Research Sheds Light on AI's 'Black Box' ” 2024 - 05 - 22

"Why do large language models behave the way that they do? New research provides some clues." >>>

“ A.I.’s Black Boxes Just Got a Little Less Mysterious ” 2024 - 05 - 22

"Researchers at the A.I. company Anthropic claim to have found clues about the inner workings of large language models, possibly helping to prevent their misuse and to curb their potential threats." >>>

“ Google CEO Sundar Pichai on AI-powered search and the future of the web ” 2024 - 05 - 22

"The head of Google sat down with Decoder last week to talk about the biggest advancements in AI, the future of Google Search, and the fate of the web." >>>

“ Europe sets benchmark for rest of the world with landmark AI laws ” 2024 - 05 - 22

"The European Union's AI Act is more comprehensive than the United States' light-touch voluntary compliance approach while China's approach aims to maintain social stability and state control." >>>

“ THE BIG AI RISK NOT ENOUGH PEOPLE ARE SEEING ” 2024 - 05 - 21

"What Herd provides here is much more than a darkly whimsical peek into a dystopian future of online dating. It's a window into a future in which people require layer upon layer of algorithmic mediation between them in order to carry out the most basic of human interactions: those involving romance, sex, friendship, comfort, food. Implicit in Herd's proclamation--that her app will "teach you how to date"-is the assumption that AI will soon understand proper human behavior in ways that human beings do not. " >>>

“ AI chatbots are intruding into online communities where people are trying to connect with other humans ” 2024 - 05 - 20

"... The most important benefits of these online spaces as described by our participants could be drastically undermined by responses coming from chatbots instead of people." >>>

“ The ‘dead internet theory’ makes eerie claims about an AI-run web. The truth is more sinister ” 2024 - 05 - 20

"The "dead internet theory" has an explanation: AI and bot-generated content has surpassed the human-generated internet. But where did this idea come from, and does it have any basis in reality?" >>>

“ Early AI models exhibit human-like errors but ChatGPT-4 outperforms humans in cognitive reflection tests ” 2024 - 05 - 20

"Researchers have discovered that OpenAI's latest generative pre-trained transformer models, commonly known as ChatGPT, can outperform humans in reasoning tasks. Published in Nature Computational Science, the study found that while early versions of these models exhibit intuitive but incorrect responses, similar to humans, ChatGPT-3.5 and ChatGPT-4 demonstrate a significant improvement in accuracy." >>>

“ Protesters Are Fighting to Stop AI, but They’re Split on How to Do It ” 2024 - 05 - 17

"The group’s main demand is for a pause on the training of AI systems more powerful than GPT-4—it’s calling for all countries to implement this measure, but specifically calls out the United States as the home of most leading AI labs. The group also wants all UN member states to sign a treaty that sets up an international AI safety agency with responsibility for granting new deployments of AI systems and training runs of large models. Their protests are taking place on the same day as OpenAI announced a new version of ChatGPT to make the chatbot act more like a human." >>>

“ Two US states seize the initiative to regulate AI ” 2024 - 05 - 17

"--Colorado and Connecticut lead AI regulation amid industry resistance, balancing innovation with safeguards.
--Connecticut's ambitious legislation faces hurdles, while Colorado navigates pressure to follow suit.
--Industry lobbying influences state-level AI regulation, raising concerns over stifling innovation." >>>

“ How to Hit Pause on AI Before It’s Too Late ” 2024 - 05 - 17

"... the real prize of human-level AI--or artificial general intelligence (AGI)--has yet to be achieved. Such a breakthrough would mean an AI that can carry out most economically productive work, engage with others, do science, build and maintain social networks, conduct politics, and carry out modern warfare. The main constraint for all these tasks today is cognition. Removing this constraint would be world-changing. Yet many across the globe's leading AI labs believe this technology could be a reality before the end of this decade." >>>

“ Google Is About to Change Everything—and Hopes You Won’t Find Out ” 2024 - 05 - 17

"It's difficult to overstate the magnitude and impact of the changes Google has been making to its search engine and overall product suite this month, some of which were laid out during Tuesday’s I/O 2024 conference. The reason is not just that parent company Alphabet is determined to shove some form of "artificial intelligence" and machine learning software into your Chrome browser and your phone calls and your photo galleries and your YouTube habits. It's that the central tool that powers and shapes the modern internet is about to permanently change--and it may make for an even worse search experience than that which has defined Google’s most recent era." >>>

“ Web publishers brace for carnage as Google adds AI answers ” 2024 - 05 - 17

"The tech giant is rolling out AI-generated answers that displace links to human-written websites, threatening millions of creators." >>>

“ AI needs the non-quants, too ” 2024 - 05 - 17

"... amid the ever-quickening pace of action, some observers wonder if government is looking at the tech industry with the right perspective. A report shared first with DFD from the nonprofit Data & Society argues that in order for powerful AI to integrate successfully with humanity, it must actually feature… the humanities." >>>

“ Google and OpenAI are racing to rewire the internet ” 2024 - 05 - 16

" Both companies are competing to build a combination of ChatGPT and Search. Now, it's a matter of who can out-maneuver the other." >>>

“ Web publishers brace for carnage as Google adds AI answers ” 2024 - 05 - 15

"... The rollout threatens the survival of the millions of creators and publishers who rely on the service for traffic. Some experts argue the addition of AI will boost the tech giant's already tight grip on the internet, ultimately ushering in a system where information is provided by just a handful of large companies." >>>

“ A.I.’s ‘Her’ Era Has Arrived ” 2024 - 05 - 15

"The company's new model, called GPT-4o (the o stands for "omni"), will let ChatGPT talk to users in a much more lifelike way -- detecting emotions in their voices, analyzing their facial expressions and changing its own tone and cadence depending on what a user wants. If you ask for a bedtime story, it can lower its voice to a whisper. If you need advice from a sassy friend, it can speak in a playful, sarcastic tone. It can even sing on command." >>>

“ In DC, a new wave of AI lobbyists gains the upper hand ” 2024 - 05 - 13

"An alliance of tech giants, startups and venture capitalists are spending millions to convince Washington that fears of an AI apocalypse are overblown. So far, it's working." >>>

“ Is AI lying to me? Scientists warn of growing capacity for deception ” 2024 - 05 - 13

"Researchers find instances of systems double-crossing opponents, bluffing, pretending to be human and modifying behaviour in tests" >>>

“ How sci-fi writer JG Ballard's computer poems predicted ChatGPT ” 2024 - 05 - 13

"In the 1970s, science fiction writer JG Ballard was intrigued by the growing capabilities of computers - so used one to compose poems. They were a first step on the road to ChatGPT." >>>

“ Meet your AI assistant for education: Microsoft Copilot ” 2024 - 05 - 13

5 ways to use Copilot in education >>>

“ The 'godmother of AI' says stop worrying about an AI apocalypse ” 2024 - 05 - 13

"AI visionary Fei-Fei Li thinks the public should instead worry about more immediate issues like AI-generated disinformation" >>>

“ OpenAI is reportedly working on a search feature for ChatGPT ” 2024 - 05 - 13

"OpenAI is reportedly working on a search feature for ChatGPT that could make the chatbot a veritable alternative to Google Search. According to Bloomberg, the company is currently developing the capability, which can scour the web for answers to your queries and spit out results complete with citations to their sources. ChatGPT could take information from Wikipedia or blog posts, for instance, and link to their original pages when you ask it questions." >>>

“ The Rise of AI: Insights from RAND ” 2024 - 05 - 13

Artificial intelligence--rom machine learning that's already widely used today to the possible artificial general intelligence of the future--has the power to transform the way we live, work, and interact.

AI tools are evolving quickly, and decisionmakers are grappling with how to maximize the potential benefits, minimize the short--and long-term risks, and plan for an uncertain future.

RAND's rigorous and independent research can help. Our experts have been studying a wide range of questions about the effects and uses of AI: Which jobs are likely to be most affected? How might AI tools be used to support military decision making? What is required to ensure that algorithms don't worsen inequity? >>>

“ OpenAI strikes licensing deal with the magazine giant behind People ” 2024 - 05 - 08

"Dotdash Meredith, publisher of People, Better Homes & Gardens, Investopedia, Food & Wine, and InStyle, signed a deal on Tuesday with OpenAI to use AI models for its ad-targeting product, D/Cipher. In turn, Dotdash Meredith will license its content to ChatGPT." >>>

“ Texas is replacing thousands of human exam graders with AI ” 2024 - 05 - 08

"Students in Texas taking their state-mandated exams this week are being used as guinea pigs for a new artificial intelligence-powered scoring system set to replace a majority of human graders in the region." >>>

“ How Generative AI Owns Higher Education. Now What? ” 2024 - 05 - 08

"It's astonishing that most professors, administrators and even donors don't see the proverbial train barreling down the tracks, perhaps like how climate deniers cannot calculate storms, rainfall, floods, droughts and unbearable summers. Maybe it’s just a repeat of the Luddite phenomenon that surrounds the adoption of all new technology. Who knows, but worse, many universities have actually banned GenAI which is a naive attempt to regulate a technology more compelling than the Internet and in so doing have actually provided encouragement to faculty and administrators to pretend that GenAI and its CustomGPT children are more of a threat than a service. Further, faculty who have not used GenAI to develop and deliver courses have already missed an extraordinary opportunity to improve the learning process for their students and increase the learning outcomes of their courses." >>>

“ Stack Overflow signs deal with OpenAI to supply data to its models ” 2024 - 05 - 07

"OpenAI is collaborating with Stack Overflow, the Q&A forum for software developers, to improve its generative AI models’ performance on programming-related tasks." >>>

“ OpenAI exec says today's ChatGPT will be 'laughably bad' in 12 months ” 2024 - 05 - 07

OpenAI COO Brad Lightcap says generative AI as it is today will be "laughably bad" within a year.

The exec predicts ChatGPT could soon take on more "complex work" and be a "great teammate."

The tech giant is set to release its latest language model, GPT-5, as early as this summer. >>>

“ ENERGY AI could drive a natural gas boom as power companies face surging electricity demand ” 2024 - 05 - 06

Natural gas producers are bullish on demand as they see significant upside from the immense energy needs of artificial intelligence and data centers.

Electricity demand is forecast to grow 20% by 2030, according to Wells Fargo.

Power companies say gas is needed to meet demand when renewable energy sources are not generating enough power. >>>

“ Tech’s new arms race: The billion-dollar battle to build AI ” 2024 - 05 - 06

"... Just as the semiconductor industry has consolidated around a handful of companies able to afford the latest multi-billion-dollar chip fabrication plants, the AI field may soon be dominated by only the largest tech giants — and their partners -- able to foot the bill for developing the latest foundation LLM models like GPT-4 and Claude 3. " >>>

“ AI Copilots Are Changing How Coding Is Taught ” 2024 - 05 - 06

"Professors are shifting away from syntax and emphasizing higher-level skills" >>>

“ What’s next with AI? ” 2024 - 04 - 28

"Consumers are already putting AI tools to use for both productivity and creativity. But what's next?" >>>

“ 10 important questions about the promise and pitfalls of AI ” 2024 - 04 - 28

"Artificial intelligence is already changing the world. But the full extent of its impact on how we live and work remains to be seen.
In the meantime, there are crucial questions to consider to help mitigate potential perils of AI on society -- and take advantage of the opportunities." >>>

“ Generative AI is still a solution in search of a problem ” 2024 - 04 - 24

The gigantic and costly industry Silicon Valley is building around generative AI is still struggling to explain the technology's utility.
Why it matters: AI chatbots and image generators are making headlines and fortunes, but a year and a half into their revolution, it remains tough to say exactly why we should all start using them. >>>

“ Jon Stewart Is Right About the Dangers of AI ” 2024 - 04 - 24

"I ... agree with the central premise of his argument that disruption caused by AI will be harnessed to prioritize profits over people. It will likely cause one of the largest and fastest labor displacements in human history." >>>

“ It’s the End of the Web as We Know It ” 2024 - 04 - 24

The web has become so interwoven with everyday life that it is easy to forget what an extraordinary accomplishment and treasure it is. In just a few decades, much of human knowledge has been collectively written up and made available to anyone with an internet connection.
But all of this is coming to an end. The advent of AI threatens to destroy the complex online ecosystem that allows writers, artists, and other creators to reach human audiences. >>>

“ AI and the End of the Human Writer ” 2024 - 04 - 24

"If a computer can write like a person, what does that say about the nature of our own creativity?" >>>

“ The bad and the ugly: AI is harmful, unreliable, and running out of data ” 2024 - 04 - 24

"Outperforming humans is one thing, but its rapid rise has meant that AI has created some problems for itself – and we're nervous." >>>

“ THE AI INDEX REPORT: Measuring trends in AI ” 2024 - 04 - 24

"Welcome to the seventh edition of the AI Index report. The 2024 Index is our most comprehensive to date and arrives at an important moment when AI's influence on society has never been more pronounced. This year, we have broadened our scope to more extensively cover essential trends such as technical advancements in AI, public perceptions of the technology, and the geopolitical dynamics surrounding its development. Featuring more original data than ever before, this edition introduces new estimates on AI training costs, detailed analyses of the responsible AI landscape, and an entirely new chapter dedicated to AI's impact on science and medicine." >>>

“ The Languages AI Is Leaving Behind ” 2024 - 04 - 24

"Generative AI is famously data-hungry. The technology requires huge troves of digital information—text, photos, video, audio-to "learn" how to produce convincingly humanlike material. The most powerful large language models have effectively "read" just about everything; when it comes to content mined from the open web, this means that AI is especially well versed in English and a handful of other languages, to the exclusion of thousands more that people speak around the world." >>>

“ AI Report Shows ‘Startlingly Rapid’ Progress—And Ballooning Costs ” 2024 - 04 - 20

"Artificial intelligence (AI) systems, such as the chatbot ChatGPT, have become so advanced that they now very nearly match or exceed human performance in tasks including reading comprehension, image classification and competition-level mathematics, according to a new report. Rapid progress in the development of these systems also means that many common benchmarks and tests for assessing them are quickly becoming obsolete." >>>

“ Q&A: Mark Zuckerberg on winning the AI race ” 2024 - 04 - 20

" Meta's CEO is pushing for the company's assistant to be the most used chatbot in the world. He opens up about competing with other AI companies, model training, and why he bought all those GPUs when he did." >>>

“ TechScape: How cheap, outsourced labour in Africa is shaping AI English ” 2024 - 04 - 20

"Workers in Africa have been exploited first by being paid a pittance to help make chatbots, then by having their own words become AI-ese. " >>>

“ How to coax ChatGPT into making better predictions: Get it to tell tales from the future ” 2024 - 04 - 20

"AI models become better at foretelling the future when asked to frame the prediction as a story about the past, boffins at Baylor University in Texas have found.
In a paper titled, "ChatGPT Can Predict the Future When It Tells Stories Set in the Future About the Past," Pham and Cunningham give away the final scene - that AI model prognostication can be effective in certain circumstances. Asking the chatbot for tales about future events rather than asking for direct predictions proved surprisingly effective, especially in forecasting Oscar winners." >>>

“ The Future of Poetry: Is AI Smarter Than an 8th Grader? ” 2024 - 04 - 15

"Write a poem about a sunrise." I asked three AI chatbots—OpenAI's ChatGPT-4, Google’s Bard, and Anthropic's Claude—and myself -- an 8th grade human. I then surveyed a panel of 38 AI experts and 39 English experts to judge the results. Is AI smarter than an 8th grader?
And the survey says . . AI is not smarter than an 8th grader, at least not yet. The 8th grader won 1st place, and by a higher margin when judged by English experts. Bard, ChatGPT-4, and Claude came in 2nd, 3rd, and 4th places, respectively, both in writing quality and their ability to fool the judges into believing they were authored by a human. Most strikingly, English experts were far better at discerning which poems were written by AI, with 11 English experts vs. only 3 AI experts guessing the author (human vs. AI) of all four poems correctly. This points to a need for English experts to play a greater role in helping shape future versions of AI technology. >>>

“ AI CEO says people's obsession with reaching artificial general intelligence is 'about creating God' ” 2024 - 04 - 14

"Mistral's CEO Arthur Mensch said the obsession with creating general AI is about "creating God."
The AI CEO doesn't believe Elon Musk and Sam Altman's predictions that AI will surpass human intelligence.
Mensch warns of tech giants imposing AI standards that conflict with global culture and values." >>>

“ ChatGPT hallucinates fake but plausible scientific citations at a staggering rate, study finds ” 2024 - 04 - 14

"A recent study has found that scientific citations generated by ChatGPT often do not correspond to real academic work. The study, published in the Canadian Psychological Association’s Mind Pad, found that "false citation rates" across various psychology subfields ranged from 6% to 60%. Surprisingly, these fabricated citations feature elements such as legitimate researchers' names and properly formatted digital object identifiers (DOIs), which could easily mislead both students and researchers." >>>

“ From boom to burst, the AI bubble is only heading in one direction ” 2024 - 04 - 14

>>>

“ The Worst Part of a Wall Street Career May Be Coming to an End ” 2024 - 04 - 14

Artificial intelligence tools can replace much of Wall Street’s entry-level white-collar work, raising tough questions about the future of finance. >>>

“ AI's 'mad cow disease' problem tramples into earnings season ” 2024 - 04 - 12

It used to be enough to mention AI on an earnings call for Wall Street to celebrate. But a more discerning reality is setting in.
Grand ambitions of AI technologies are propped up by gargantuan costs - from extreme demands on natural resources to immense hardware investments. Big Tech's enormous valuations seem less justified, butting up against the improbable state of affairs in AI development.
If 2024 is the "show me" year, we're still waiting. >>>

“ What if Dario Amodei Is Right about A.I.? ” 2024 - 04 - 12

An Ezra Klein podcast:
"Back in 2018, Dario Amodei worked at OpenAI. And looking at one of its first A.I. models, he wondered: What would happen as you fed an artificial intelligence more and more data?
He and his colleagues decided to study it, and they found that the A.I. didn’t just get better with more data; it got better exponentially. The curve of the A.I.’s capabilities rose slowly at first and then shot up like a hockey stick. " >>>

“ Anthropic says its AI models are as persuasive as humans ” 2024 - 04 - 12

"AI startup Anthropic says its language models have steadily and rapidly improved in their "persuasiveness," per new research the company posted Tuesday.
Why it matters: Persuasion -- a general skill with widespread social, commercial and political applications -- can foster disinformation and push people to act against their own interests, according to the paper's authors." >>>

“ How Generative AI Now Owns Higher Education. Now What? ” 2024 - 03 - 19

Let's assume that you’re "teaching" a course. Now let's assume that you’re taking a course or have enrolled in a degree program. Let's also assume that you know something about generative AI (GenAI) which many professors and lot’s more students already do. Let's also assume that GenAI tools will become incredibly smarter, better and faster, which is the easiest prediction anyone can make.
If all of the above assumptions are true – and they obviously are - what happens to higher education?
Have we missed something huge here? >>>

“ How generative AI will change low-code development ” 2024 - 03 - 17

Coding will become almost entirely automated, and UX designers will become the de facto front-end developer,” says David Brooks, senior VP and lead evangelist at Copado. “Instead of graphics tools like Figma to mock up UI, they will work with genAI tools to generate working UI prototypes in the company’s framework of choice.” >>>

“ How to write better ChatGPT prompts in 5 steps ” 2024 - 02 - 24

"There's an art to making the most from AI. Here's how to up your prompt-writing game." >>>

“ What Are AI Text Generators? 8 Best Tools To Improve Writing ” 2024 - 02 - 19

>>>

“ 'Rat Dck' Among Gibberish AI Images Published in Science Journal ” 2024 - 02 - 17

"Bizarre, clearly inaccurate imagery created by Midjourney skated past peer-review at a well-known journal." >>>

“ AI won't take our jobs and it might even save the middle class ” 2024 - 02 - 16

"The future described in OpenAI's mission statement, in which autonomous systems "outperform humans at most economically valuable work," sounds like a hellscape to MIT economics professor David Autor.
A world where humans supply only generic, undifferentiated labor and wealth flows to AI system owners and rights holders would look something like "WALL-E" meets "Mad Max," he says.
But it doesn't have to be that way. ..." >>>

“ When Your Technical Skills Are Eclipsed, Your Humanity Will Matter More Than Ever ” 2024 - 02 - 16

"There have been just a handful of moments over the centuries when we have experienced a huge shift in the skills our economy values most. We are entering one such moment now. Technical and data skills that have been highly sought after for decades appear to be among the most exposed to advances in artificial intelligence. But other skills, particularly the people skills that we have long undervalued as soft, will very likely remain the most durable. That is a hopeful sign that A.I. could usher in a world of work that is anchored more, not less, around human ability." >>>

“ ChatGPT will kill off the Romantic genius ” 2024 - 01 - 31

Every author, in his or her individual way, is a meat-brained ChatGPT, “trained” on a lifetime’s reading of classics and copyright works. >>>

“ I'm LinkedIn’s chief economist and this is how AI will change the global labor market (but not how you think) ” 2023 - 12 - 20

"Employers are increasingly looking for skills, and in the past year, AI skills and complementary people skills have been rising to the top, with demand coming from virtually every industry and spanning both technical and non-technical roles. In parallel, demand for people skills that complement AI is also rising. A majority (92%) of U.S. executives agree that people skills are more important than ever. " >>>

“ While ChatGPT stokes fears of mass layoffs, new jobs are being spawned to review AI ” 2023 - 10 - 13

Since Nov. 2022, global business leaders, workers and academics alike have been gripped by fears that the emergence of generative AI will disrupt vast numbers of professional jobs.

But the inputs that AI models receive, and the outputs they create, often need to be guided and reviewed by humans — and this is creating new paid careers and side hustles.

Prolific, a company that helps connect AI developers with research participants, has had direct involvement in providing people with compensation for reviewing AI-generated material. >>>

“ How To Turn ChatGPT Into Your Ultimate Personal Writing Assistant ” 2023 - 10 - 13

When I first started using ChatGPT, I made one crucial mistake: I expected it to think rather than do. I fed it poorly written, one-sentence prompts and expected some magical output.
Unfortunately, poor instructions led to poor results. To turn things around, I had to reframe my perspective. >>>

“ Microsoft Outlook will soon write emails for you ” 2023 - 10 - 13

Artificial intelligence could soon be writing more company emails in Microsoft Outlook, as the company expands its rollout of AI tools for corporate users. >>>

“ AI just got 100-fold more energy efficient ” 2023 - 10 - 13

Northwestern University engineers have developed a new nanoelectronic device that can perform accurate machine-learning classification tasks in the most energy-efficient manner yet. Using 100-fold less energy than current technologies, the device can crunch large amounts of data and perform artificial intelligence (AI) tasks in real time without beaming data to the cloud for analysis. >>>

“ What Do ChatGPT’s New Capabilities Really Mean For Us All? ” 2023 - 10 - 13

I’ll bet that most people who have tried have found at least one useful way to integrate ChatGPT into their lives now. Much is written about the potential of AI to help us cure cancer or fight climate change. But I firmly believe its potential to help us in our day-to-day lives, redefining our relationship with technology, will be just as revolutionary.
Which is why it's always interesting to see new updates and capabilities added. The latest updates, however, are particularly thought-provoking. >>>

“ America’s secret asset against AI workforce takeover ” 2023 - 10 - 13

Overcoming ageism in our workplaces is the first step in adapting to a new world of work. >>>

“ Generative AI in commerce: 5 ways industries are changing how they do business ” 2023 - 10 - 13

Generative technology, such as ChatGPT, can transform commerce in a range of ways, including knowledge distribution, HR and training, code writing, legal, cybersecurity, treasury, marketing, customer interfaces, and service delivery, according to the report. >>>

“ How genAI is revolutionizing the field of economics ” 2023 - 10 - 13

Anton Korinek, an economics professor at the University of Virginia, tells the students he advises nowadays that they should really begin to master a flourishing technology expected to transform the field of economics. That technology is generative artificial intelligence, or “genAI” for short. >>>

“ Google promises to take the legal heat in users’ AI copyright lawsuits ” 2023 - 10 - 13

The company says it will take responsibility for its training data and the output of its foundation models. >>>

“ Why ChatGPT Talks the Talk but Doesn’t Walk the Walk ” 2023 - 10 - 12

Many wonder how the intelligence of large language models compares to human intelligence.

Humans have an advantage in learning speed and flexibility in applying what they have learned.

Humans remain unique in their ability to respond relationally, the foundation of intelligent behavior. >>>

“ The Homework Apocalypse ” 2023 - 10 - 12

Students will cheat with AI. But they also will begin to integrate AI into everything they do, raising new questions for educators. Students will want to understand why they are doing assignments that seem obsolete thanks to AI. They will want to use AI as a learning companion, a co-author, or a teammate. They will want to accomplish more than they did before, and also want answers about what AI means for their future learning paths. Schools will need to decide how to respond to this flood of questions.
The challenge of AI in education can feel abstract, so to understand a bit more about what is going to happen, I wanted to examine some common assignment types. >>>

“ The Environmental Impact of LLMs ” 2023 - 10 - 11

With the adoption of LLMs, there’s a new concern gaining ground – the environmental impact of training these models. Believe it or not, the carbon footprints left behind from training large models run into hundreds of tonnes. >>>

“ Energy consumption of AI poses environmental problems ” 2023 - 10 - 11

Training an advanced AI model takes time, money and high-quality data. It also takes energy -- a lot of it.
Between storing data in large-scale data centers and then using that data to train a machine learning or deep learning model, AI energy consumption is high. While an AI system may pay off monetarily, AI poses a problem environmentally. >>>

“ TECH Calls for AI regulations to protect jobs rise in Europe after ChatGPT’s arrival ” 2023 - 10 - 11

An IE University study showed that, out of a sample of 3,000 Europeans, 68% want their governments to introduce rules to safeguard jobs from AI advancement.

That number is up 18% from the amount of people who responded in the same way to a similar piece of research that IE University brought out in 2022.

It comes as governments around the world are working on regulation for AI algorithms. >>>

“ The environmental impact of the AI revolution is starting to come into focus ” 2023 - 10 - 11

Google's use of AI alone could use up as much electricity as a small country - but that's an unlikely worst-case scenario, a new analysis finds. >>>

“ Big Tech Struggles to Turn AI Hype Into Profits ” 2023 - 10 - 11

Microsoft, Google and others experiment with how to produce, market and charge for new tools. >>>

“ So far, AI hasn’t been profitable for Big Tech ” 2023 - 10 - 11

Microsoft loses around $20 per user per month on GitHub Copilot, according to the WSJ.
Big Tech companies like Microsoft and Google are grappling with the challenge of turning AI products like ChatGPT into a profitable enterprise, reports The Wall Street Journal. While companies are heavily investing in AI tech that can generate business memos or code, the cost of running advanced AI models is proving to be a significant hurdle. Some services, like Microsoft's GitHub Copilot, drive significant operational losses. >>>

“ Why AI is teetering on the edge of a disillusionment cliff | The AI Beat ” 2023 - 10 - 04

The bottom line is that AI may have incredible positive potential for humanity’s future, but I don’t think companies are doing a great job of communicating what that is. Where is the “why” — as in, why are we going through all the angst of building all of this? What is the current and future value of generative AI to individuals, workers, enterprises, and society at large? How do the benefits outweigh the risks? >>>

“ AI is coming to the Arc browser — but probably not like you think ” 2023 - 10 - 04

Sure, you could just stick a ChatGPT sidebar in your browser. But what do we really want AI to do for us as we use the web? That’s the much harder question. (See Arc Ma) >>>

“ Artists Are Losing the War Against AI ” 2023 - 10 - 04

OpenAI has introduced a tool for artists to keep their images from training future AI programs. It may not make a difference. >>>

“ What does generative AI mean for software companies? ” 2023 - 10 - 04

Some of the initial changes will be felt in day-to-day maneuvers and staffing structures. AI will mean that routine and basic code writing will be displaced and generated automatically. Consequently, manual programming and the roles of coders and developers will move to creative and more sophisticated tasks. >>>

“ Generative AI will far surpass what ChatGPT can do. Here's everything on how the tech advances ” 2023 - 10 - 04

What does the future of generative AI hold? Multi-modality will move a primitive ChatGPT demo to interpersonal collaboration, advanced robotics -- and maybe even the AI dream of continuous learning. >>>

“ The synthetic social network is coming ” 2023 - 10 - 04

Between ChatGPT’s surprisingly human voice and Meta’s AI characters, our feeds may be about to change forever >>>

“ Enterprise workers gain 40 percent performance boost from GPT-4, Harvard study finds ” 2023 - 10 - 04

A Harvard-led study has found that using generative AI helped hundreds of consultants working for the respected Boston Consulting Group (BCG) complete a range of tasks more often, more quickly, and at a higher quality than those who did not use AI. >>>

“ Latest Prompt Engineering Technique Chain-Of-Verification Does A Sleek Job Of Keeping Generative AI Honest And Upright ” 2023 - 10 - 04

[This article is worth reading because it also contains links to further suggestions about prompt-crafting]
(1) Enter your initial prompt. This is the initiating prompt that gets the generative AI to produce an answer or essay to whatever question or problem you want to have solved.
(2) Look at the GenAI initial response to the prompt. This is the initial answer or response that the AI app provides to your prompt.
(3) Establish suitable verification questions. Based on the generative AI output, come up with pertinent verification questions.
(4) Ask GenAI the verification questions. Enter a prompt or series of prompts that ask the generative AI the identified verification questions.
(5) Inspect the answers to the verification questions. Take a look at the answers to the verification questions, weighing them in light of what they might signify regarding the GenAI initial response.
(6) Adjust or refine the initial answer accordingly. If the verification answers warrant doing so, go ahead and refine or adjust the initial answer as needed. >>>

“ If you have one of these 10 jobs, AI has some of the skills to replace you ” 2023 - 10 - 04

>>>

“ AI-focused tech firms locked in ‘race to the bottom’, warns MIT professor ” 2023 - 09 - 21

he scientist behind a landmark letter calling for a pause in developing powerful artificial intelligence systems has said tech executives did not halt their work because they are locked in a "race to the bottom". >>>

“ HustleGPT: Generative AI will boost income and help millions of workers take on second and third jobs, Morgan Stanley predicts. ” 2023 - 09 - 21

Generative AI is making it easier to work multiple jobs at the same time.

AI tools will lift earnings from multiple jobs by at least $83 billion by 2030, Morgan Stanley says.

Multi-earning in the US has increased 11% in the past year, the bank's survey work found. >>>

“ Concerns Over "Digital Necromancy" Overblown, According to Experts ” 2023 - 09 - 21

Generative AI – which encompasses large language models (LLMs) like ChatGPT but also image and video generators like DALL·E 2 – supercharges what has come to be known as "digital necromancy", the conjuring of the dead from the digital traces they leave behind.

Debates around digital necromancy were first sparked in the 2010s by advances in video projection ("deep fake" technology) leading to the reanimation of Bruce Lee, Michael Jackson, and Tupac Shakur. It also led to posthumous film appearances by Carrie Fisher and Peter Cushing, among others. >>>

“ Stuart Russell wrote the textbook on AI safety. He explains how to keep it from spiraling out of control. ” 2023 - 09 - 21

One of the hardest parts of the news business is striking a balance between covering stories that seem important in the moment and covering stories that you know will truly matter in the future. And it’s hard because the most consequential things happening right now are often boring or difficult to explain. >>>

“ Franzen, Grisham and Other Prominent Authors Sue OpenAI ” 2023 - 09 - 21

The suit, filed with the Authors Guild, accuses the A.I. company of infringing on authors’ copyrights, claiming it used their books to train its ChatGPT chatbot. >>>

“ AI’s existential threat is a ‘completely bonkers distraction’ because there are ‘like 101 more practical issues’ to talk about, top founder in the field says ” 2023 - 09 - 21

>>>

“ This free AI tool can write your cover letters, and is easier to use than ChatGPT ” 2023 - 09 - 21

When looking for a job, you're likely applying to several positions at a time -- each requiring a uniquely hand-crafted application. Cover Letter Copilot has you covered. >>>

“ New Study: AI Chatbots Surpass the Average Human in Creativity ” 2023 - 09 - 21

A recent study published in the journal Scientific Reports suggests that large language model (LLM) AI chatbots might excel beyond the average human in creative tasks, like brainstorming alternate uses for common items – a reflection of divergent thinking. However, individuals who scored the highest in these tasks still surpassed the top-performing chatbot results. >>>

“ DeepMind’s cofounder: Generative AI is just a phase. What’s next is interactive AI. ” 2023 - 09 - 21

DeepMind cofounder Mustafa Suleyman wants to build a chatbot that does a whole lot more than chat. In a recent conversation I had with him, he told me that generative AI is just a phase. What’s next is interactive AI: bots that can carry out tasks you set for them by calling on other software and other people to get stuff done. He also calls for robust regulation—and doesn’t think that’ll be hard to achieve. >>>

“ 5 ChatGPT Prompts To Feel Invincible At Work ” 2023 - 09 - 12

>>>

“ Why Human Writing Is Worth Defending In the Age of ChatGPT ” 2023 - 09 - 12

A specter is haunting the landscape—the specter of generative AI. First came fears that student cheating would explode, plus that artists and actors would be unemployed. Then the ante was upped: Some of the very technology’s creators warned that AI’s potential risk to humanity as we know it was on par with pandemics and nuclear war. >>>

“ The modern CEO job is completely broken — but AI could make executives useful again ” 2023 - 09 - 12

rom writers and teachers to bankers and lawyers, most jobs seem ripe to be replaced by artificial intelligence — with one notable exception. The only job that seems to be safe from the rise of ChatGPT and other AI tech is, oddly enough, the most expensive and easily automated role: CEO. >>>

“ Generative AI Generation Gap: 70% Of Gen Z Use It While Gen X, Boomers Don’t Get It ” 2023 - 09 - 12

75% of people who use generative AI use it for work and 70% of Gen Z uses new generative AI technologies, according to a new 4,000-person survey by Salesforce, which has been integrating AI into its products for years. Also found: 68% of those who haven’t tried generative AI are Gen X or boomers. >>>

“ How to write books using AI with Claude 2.0 ” 2023 - 09 - 05

Writers and authors interested in learning more about how they can use large language models and artificial intelligence to enhance their writing skills. Might be interested in this new video on how to write a complete book using the Claude 2.0 AI. The Nerdy Novelist, a popular YouTube channel dedicated to the craft of writing, recently explored the potential of this AI tool in the creation of an entire book. >>>

“ People Are Increasingly Worried AI Will Make Daily Life Worse ” 2023 - 09 - 05

A Pew survey finds that a majority of Americans are more concerned than excited about the impact of artificial intelligence—adding weight to calls for more regulation. >>>

“ Pew Research finds a big problem with AI: People don’t trust it ” 2023 - 09 - 05

If companies want their employees to embrace the potential of generative AI, they're going to have to make sure those workers actually trust it won't cost them their jobs. Share on Facebook Share on Twitter Share on LinkedIn Share on Reddit Share by Email Print resource >>>

“ Survey finds relatively few Americans actually use (or fear) ChatGPT ” 2023 - 08 - 30

From its prominence in the tech world, you might think that everyone on the planet is using ChatGPT or some other AI tool for everything from automating their job to planning their garden. But recent Pew polling suggests the language model isn’t quite as popular or threatening as some would have you think. >>>

“ 3 Steps To Make ChatGPT Your Personal Twitter (X) Copywriter ” 2023 - 08 - 30

"I'd like some help composing tweets for my brand. They're going to be promotional tweets, and I want them to be really compelling. The primary target audience for the tweets is [describe audience]. One of their biggest concerns is [describe biggest pain point]. One of their biggest underutilised assets is [describe their underutilised assets]. Our solution is [explain your business]. Do you understand what I'm looking for? Don't create any tweets yet." >>>

“ US Copyright Office wants to hear what people think about AI and copyright ” 2023 - 08 - 30

As announced in the Federal Register, the agency wants to answer three main questions: how AI models should use copyrighted data in training; whether AI-generated material can be copyrighted even without a human involved; and how copyright liability would work with AI. It also wants comments around AI possibly violating publicity rights but noted these are not technically copyright issues. The Copyright Office said if AI does mimic voices, likenesses, or art styles, it may impact state-mandated rules around publicity and unfair competition laws. >>>

“ Google stock rises as it says it will charge $30 for enterprise AI service ” 2023 - 08 - 30

Shares of Google parent Alphabet (GOOG, GOOGL) jumped on Tuesday, as the tech giant debuted a slew of new AI offerings for its Google Cloud and Workspace enterprise platforms. The news comes as part of Google’s annual Google Cloud Next event, which is being held in San Francisco. >>>

“ The Daily Scoop: Another journalism outlet flounders with challenges of AI ” 2023 - 08 - 30

Even when things went right, the briefs weren't great. But often things went wrong. Social media users noted that odd phrases like "close encounters of the athletic kind" cropped up in story after story -- a phrase that doesn’t make sense to begin with but is even worse when repeated. And while the ethical standards of papers like the Columbus Dispatch say that "AI-generated content must be verified for accuracy and factuality before used in reporting," Axios reported that in at least one case, a story was published that had clear placeholders for "[[WINNING_TEAM_MASCOT]]." >>>

“ AI is killing the grand bargain at the heart of the web. 'We're in a different world.' ” 2023 - 08 - 30

At the time, the main purpose of these crawlers was to index information so results in search engines would improve. Google, Microsoft's Bing and other search engines have crawlers. They index content so it can be later served up as links to billions of potential consumers. This is the essential deal that created the flourishing web we know today: Creators share abundant information and exchange ideas online freely because they know consumers will visit and either see an ad, subscribe, or buy something.
Now, though, generative AI and large language models are changing the mission of web crawlers radically and rapidly. Instead of working to support content creators, these tools have been turned against them. >>>

“ How to Use Bing AI in Google Chrome ” 2023 - 08 - 29

>>>

“ Prompt engineering: is being an AI ‘whisperer’ the job of the future or a short-lived fad? ” 2023 - 08 - 29

The germ of truth in the “anyone can do it” narrative is that experts in a particular subject are often the best prompters for a defined task. They simply know the right questions to ask and can recognise value in the responses. >>>

“ IBM could replace 7,800 jobs with artificial intelligence, CEO says ” 2023 - 08 - 29

IBM Corp. said it expects to pause hiring for jobs that artificial intelligence could do, indicating that the potentially groundbreaking technology is beginning to disrupt how humans work. >>>

“ Using ChatGPT to Make Better Decisions ” 2023 - 08 - 29

Can ChatGPT help executives make better decisions? The large language model everyone has been talking about for months also has an eloquent answer to this question: "Yes, I can support you in management decisions by providing information, facts, analysis, and perspectives that can help you make an informed decision." ChatGPT immediately follows up with a limitation of its own competence. "However, it is important to note that my advice and recommendations are based on an algorithmic analysis of data and information, and you, as a human being, still have to make the final decision based on your experience, knowledge, and assessment of the situation." >>>

“ The A.I. Revolution Is Coming. But Not as Fast as Some People Think ” 2023 - 08 - 29

From steam power to the internet, there has always been a lag between technology invention and adoption across industries and the economy. >>>

“ 6 ChatGPT prompt secrets to improve your writing ” 2023 - 08 - 28

The secret to unlocking the full potential of ChatGPT lies in combining all the components – action, format, role, tone, audience, examples, and format – in a single prompt. This approach can yield a more comprehensive and satisfactory result, making ChatGPT an indispensable tool for writers. >>>

“ ChatGPT vs Bing vs Bard vs Claude comparison which ones right for you? ” 2023 - 08 - 28

The choice between ChatGPT, Google Bard, Microsoft Bing, and Claude 2.0 depends on your specific needs and preferences. The best bet is to try out everything that is on offer and see which provides the best results on the prompts that you provide. Remember all large language models provide results relative to the prompts they are given so writing a specific text prompt that is tailored to your exact requirements is paramount. >>>

“ AI safety and bias: Untangling the complex chain of AI training ” 2023 - 08 - 28

AI is progressing at a rapid pace. If we don't build safe systems now, we never will, says Intel researcher Lama Nachman. >>>

“ Stephen King shares his thoughts on AI writing fiction ” 2023 - 08 - 25

"I view this possibility with a certain dreadful fascination." >>>

“ In Reversal Because of A.I., Office Jobs Are Now More at Risk ” 2023 - 08 - 25

Technology disruption typically affected blue-collar occupations. Now white-collar workers may feel the brunt of changes. >>>

“ M.F.A. vs. GPT: How to push the art of writing out of a computer’s reach ” 2023 - 08 - 25

>>>

“ Bing Chat Is More Than a ChatGPT Clone ” 2023 - 08 - 25

Here's all the cool things you can do with Bing Chat in Edge. >>>

“ Why you should use ChatGPT on your resume, says ex-Google recruiter: These tools ‘make you better’ ” 2023 - 08 - 25

It is “the ultimate resume-writing cheat code,” career strategist Madelyn Machado previously told CNBC Make It. And there are various ways to you use it. You can ask the bot to optimize your resume for a given role, for example, or ask it to pull out keywords from a job description to include on your resume. >>>

“ Cutting Through The Hype Cycle Of Generative AI ” 2023 - 08 - 25

>>>

“ 40% of workers will have to reskill in the next three years due to AI, says IBM study ” 2023 - 08 - 20

"AI won't replace people—but people who use AI will replace people who don't," said IBM in the report. >>>

“ Is the AI boom already over? ” 2023 - 08 - 20

Generative AI tools are generating less interest than just a few months ago. >>>

“ Google's AI-Powered Tool Summarizes Web Pages for Instant Insights ” 2023 - 08 - 16

Google's AI-powered version of Search, called Search Generative Experience, is getting a major update in the Google App and soon in the Chrome web browser. SGE will be able to summarize web pages and also show you definitions of words you may be unfamiliar with, Google said in a blog post Tuesday. >>>

“ When Hackers Descended to Test A.I., They Found Flaws Aplenty ” 2023 - 08 - 16

The hackers had the blessing of the White House and leading A.I. companies, which want to learn about vulnerabilities before those with nefarious intentions do. >>>

“ Google Tests an A.I. Assistant That Offers Life Advice ” 2023 - 08 - 16

The tech giant is evaluating tools that would use artificial intelligence to perform tasks that some of its researchers have said should be avoided. >>>

“ Google's next big swing at AI rumored to launch this fall ” 2023 - 08 - 16

An anonymous source involved with the product — known as Gemini — recently provided new details on Google’s plans, as reported by The Information. Rather than simply compete with products such as ChatGPT, Google intends to surpass its competition with Gemini. The source specifies that it is focused on combining the text capabilities of its large language models (LLMs) and AI image generation to create a multifunctional product. This means that instead of only being able to generate text, like ChatGPT, Gemini would be able to create contextual images — but Google is reportedly looking into adding other features as well. >>>

“ How to Use ChatGPT to Write a Resume: Simple, Fast, Effective ” 2023 - 08 - 14

So you've decided to try out artificial intelligence to help speed up your process. When it comes to AI and ChatGPT, the use cases are seemingly endless, but here are four ways to start to leverage ChatGPT for your resume. >>>

“ Why the Great AI Backlash Came for a Tiny Startup You’ve Probably Never Heard Of ” 2023 - 08 - 14

A literary analytics project called Prosecraft has shuttered after backlash from the writing community. It's a harbinger of a bigger cultural tide shift. >>>

“ ChatGPT's odds of getting code questions correct are worse than a coin flip ” 2023 - 08 - 14

ChatGPT, OpenAI's fabulating chatbot, produces wrong answers to software programming questions more than half the time, according to a study from Purdue University. That said, the bot was convincing enough to fool a third of participants. >>>

“ 5 ChatGPT Prompts To Become A Better Negotiator ” 2023 - 08 - 13

When trying these prompts, have a specific situation in mind. Dig into a client challenge that’s been bugging you recently, explain an employee conundrum that you’d just love to solve, or visualize the future and get ahead of anything that’s likely to come up. >>>

“ Fiction writers fear the rise of AI, but also see it as a story to tell ” 2023 - 08 - 13

NEW YORK -- For a vast number of book writers, artificial intelligence is a threat to their livelihood and the very idea of creativity. More than 10,000 of them endorsed an open letter from the Authors Guild this summer, urging AI companies not to use copyrighted work without permission or compensation.
At the same time, AI is a story to tell, and no longer just in science fiction. >>>

“ College professors are considering creative ways to stop students from using AI to cheat ” 2023 - 08 - 13

Other academics are considering more drastic action.
"I'm planning on going medieval on the students and going all the way back to oral exams," Christopher Bartel, a philosophy professor at Appalachian State University, said. "They can AI generate text all day long in their notes if they want, but if they have to be able to speak it, that's a different thing." >>>

“ We Asked AI to Write Eminem’s “My Name Is” for Abraham Lincoln – Check Out the Results ” 2023 - 08 - 13

>>>

“ These Women Tried to Warn Us About AI ” 2023 - 08 - 13

IMNIT GEBRU DIDN'T set out to work in AI. At Stanford, she studied electrical engineering --getting both a bachelor’s and a master’s in the field. Then she became interested in image analysis, getting her Ph.D. in computer vision. When she moved over to AI, though, it was immediately clear that there was something very wrong.
"There were no Black people -- literally no Black people," says Gebru, who was born and raised in Ethiopia. "I would go to academic conferences in AI, and I would see four or five Black people out of five, six, seven thousand people internationally. I saw who was building the AI systems and their attitudes and their points of view. I saw what they were being used for, and I was like, 'Oh, my God, we have a problem.'" >>>

“ AI could have bigger impact on UK than Industrial Revolution ” 2023 - 08 - 12

Artificial intelligence could have a more significant impact on Britain than the Industrial Revolution, the deputy prime minister has said, but warned it could be used by hackers to access sensitive information from the government.
Oliver Dowden said AI could speed up productivity and perform boring aspects of jobs. >>>

“ An author says AI is ‘writing’ unauthorized books being sold under her name on Amazon ” 2023 - 08 - 12

Jane Friedman, who has authored multiple books and consulted about working in the writing and publishing industry, told CNN that an eagle-eyed reader looking for more of her work bought one of the fake titles on Amazon. The books had titles similar to the subjects she typically writes about, but the text read as if someone had used a generative AI model to imitate her style. >>>

“ With “thanabots,” ChatGPT is making it possible to talk to the dead ” 2023 - 08 - 07

hatGPT is making it possible to digitally resurrect the dead in the form of thanabots: chatbots trained on data of the deceased. A program called Project December already allows users to input information about a person and have a custom chatbot created for them based on that person. As Facebook, Google, Apple, and Microsoft all store heaps of our digital communications, it's conceivable that they all could create and sell thanabots in the coming years. >>>

“ A.I.’s Inroads in Publishing Touch Off Fear, and Creativity ” 2023 - 08 - 07

The arrival of Amazon reshaped the retail landscape for books. The rise of e-books threatened the printed word. And the boom in self publishing gave writers a path to success that left out traditional publishing houses. Each time, the book business was able to adapt.
Now, publishing is facing a new disruption that is likely to be far more wide-ranging and transformative: the rise of artificial intelligence. >>>

“ Why graphic designers think generative A.I. needs them as much as they need it ” 2023 - 08 - 07

Design professionals are betting that without the spark of human creativity in the form of a prompt for the AI, the technology won’t be able to recreate what they do across product, advertising and marketing campaigns. >>>

“ Age of AI: Everything you need to know about artificial intelligence ” 2023 - 08 - 07

Breaking down the jargon, an overview of the major players and staying up-to-date on the latest AI news >>>

“ 6 New ChatGPT Features Include Prompt Examples & File Uploads ” 2023 - 08 - 04

OpenAI is introducing several upgrades to ChatGPT, including suggested replies, keyboard shortcuts, and longer log-in durations. Prompt examples are designed to make starting a new chat less intimidating for users. Multi-file upload capabilities can aid in thorough analysis and extraction of insights. >>>

“ Death by LLM: Stack Overflow's decline, and its plan to survive, shows the future of free online data in an AI world ” 2023 - 08 - 04

Stack Overflow, an online community for software coders, has seen traffic fall since GPT-4 came out. Some AI models that compete against Stack Overflow were partly trained on the company's data. Its CEO, Prashanth Chandrasekar, says he's responding in two main ways. >>>

“ Google's AI-powered search is learning to give credit where it's due ” 2023 - 08 - 04

Despite the ease with which generative AI serves up content that would otherwise take humans hours to complete, a major concern remains: plagiarized text. This is particularly true with Google's ChatGPT rival, Bard, for which the search giant was recently slapped with a class-action lawsuit for allegedly stealing vast amounts of data from the web to train the AI tool. >>>

“ A jargon-free explanation of how AI large language models work ” 2023 - 08 - 04

When ChatGPT was introduced last fall, it sent shockwaves through the technology industry and the larger world. Machine learning researchers had been experimenting with large language models (LLMs) for a few years by that point, but the general public had not been paying close attention and didn’t realize how powerful they had become.
Today, almost everyone has heard about LLMs, and tens of millions of people have tried them out. But not very many people understand how they work. >>>

“ A.I. is on a collision course with white-collar, high-paid jobs — and with unknown impact ” 2023 - 08 - 04

About 1 in 5 American workers have a job with “high exposure” to artificial intelligence, according to Pew Research Center. It’s unclear if AI would enhance or displace these jobs.
Workers with the most exposure to AI like ChatGPT tend to be women, white or Asian, higher earners and have a college degree, Pew found. >>>

“ When A.I. Lies About You, There’s Little Recourse. ” 2023 - 08 - 03

People have little protection or recourse when the technology creates and spreads falsehoods about them. >>>

“ ChatGPT is much better than humans at accurately identifying emotions in fictional textual scenarios ” 2023 - 08 - 03

A new study found that ChatGPT, an increasingly popular AI chatbot capable of natural language processing, greatly outperformed humans in emotional awareness tasks in a set of fictional textual scenarios. It was much better than typical people at estimating the emotions characters would likely experience. The paper was published in Frontiers in Psychology. >>>

“ ChatGPT can turn bad writers into better ones ” 2023 - 07 - 31

"People who use ChatGPT to help with writing tasks are more productive and produce higher-quality work than those who don’t, a study found." >>>

“ CNET Is Reviewing the Accuracy of All Its AI-Written Articles After Multiple Major Corrections ” 2023 - 07 - 31

Aside from stringing together human-like, fluid English language sentences, one of ChatGPT’s biggest skillsets seems to be getting things wrong. In the pursuit of generating passable paragraphs, the AI-program fabricates information and bungles facts like nobody’s business. Unfortunately, tech outlet CNET decided to make AI’s mistakes its business. >>>

“ Level Up Your Resume Using ChatGPT In A Few Minutes ” 2023 - 07 - 31

You don’t need ChatGPT to create your entire resume, but it can certainly take it to the next level and keep you ahead of the competition. >>>

“ Hope, fear, and AI ” 2023 - 07 - 31

We polled 2,000 people about how they’re using AI, what they want it to do, and what scares them about it the most. >>>

“ OpenAI, Google will watermark AI-generated content to hinder deepfakes, misinfo ” 2023 - 07 - 23

"Seven companies—including OpenAI, Microsoft, Google, Meta, Amazon, Anthropic, and Inflection—have committed to developing tech to clearly watermark AI-generated content. That will help make it safer to share AI-generated text, video, audio, and images without misleading others about the authenticity of that content, the Biden administration hopes." >>>

“ Warming Up to the Power of ChatGPT ” 2023 - 07 - 16

"If much of the boilerplate text of form letters and weather reporting gets generated by ChatGPT, the differences between these dull but useful forms of communication and, say, the surprises found in a human-generated love letter or sonnet about a summer day could become easier to see—and more widely appreciated." >>>

“ The Oncoming AI Ed-Tech ‘Tsunami’ ” 2023 - 04 - 18

The AI-in-education market is expected to grow from approximately $2 billion in 2022 to more than $25 billion in 2030, with North America accounting for the largest share.
Artificial intelligence is expected to begin outperforming humans on most cognitive tasks this century, according to experts. >>>

“ Chegg pitches itself as an AI middleman ” 2023 - 04 - 18

Educational software company Chegg (CHGG.N) is trying to stay one step ahead of artificial intelligence. Its 8.2 million student subscribers could easily turn to free AI-powered chatbots like ChatGPT as an alternative aid for homework and test prep. But the bot’s propensity to spit out false information and role in enabling cheating has led some schools to ban it. With its stock down 40% since ChatGPT’s November release, Chegg has a new plan to act as an intermediary between students and AI. Finding a way to put a friendly face on the technology might be a smart strategy for other at-risk industries. >>>

“ This is the ultimate, no BS ChatGPT cheat sheet for UX and UI designers ” 2023 - 04 - 18

AI will offer designers new tools and capabilities to increase their efficiency and creativity. In this post, we’ll explore why AI won’t replace designers, but rather enhance their work.
This blog is an attempt to the personal mission of mine at gethired.design to build superpower designers who can become recession proof. So, let’s talk about how to embrace ChatGPT to become irreplaceable in your team. >>>

“ AI music will bring unchained melodies to your ear ” 2023 - 04 - 18

ChatGPT and artificial intelligence have the potential to revolutionize music by creating sounds and melodies beyond the abilities of human voices and musical instruments, tech experts say. However, machines may never replace human creativity.
"You’re going to have amateur creators, individuals who just love creating music in their homes, tinkering with AI music creation tools, just playing with it. Finally — one, two, maybe a dozen of those people are going to be able to create something that is super, super cool that then gets picked up by the general public." >>>

“ ChatGPT Can Decode Fed Speak, Predict Stock Moves From Headlines ” 2023 - 04 - 18

The first wave of academic research applying ChatGPT to the world of finance is arriving — and judging by early results, the hype of the past few months is justified.
Two new papers have been published this month that deployed the artificial intelligence chatbot in market-relevant tasks — one in deciphering whether Federal Reserve statements were hawkish or dovish, and one in determining whether headlines were good or bad for a stock. >>>

“ How to test what an AI model can — and shouldn’t — do ” 2023 - 03 - 31

Inside the labs that helps evaluate AI safety for models like GPT-4 >>>

“ The Age of AI has begun ” 2023 - 03 - 31

In my lifetime, I’ve seen two demonstrations of technology that struck me as revolutionary. The first time was in 1980, when I was introduced to a graphical user interface—the forerunner of every modern operating system, including Windows. I sat with the person who had shown me the demo, a brilliant programmer named Charles Simonyi, and we immediately started brainstorming about all the things we could do with such a user-friendly approach to computing. Charles eventually joined Microsoft, Windows became the backbone of Microsoft, and the thinking we did after that demo helped set the company’s agenda for the next 15 years.
The second big surprise came just last year. I’d been meeting with the team from OpenAI since 2016 and was impressed by their steady progress. In mid-2022 . . . >>>

“ Italy Bans ChatGPT and Says It Will Investigate OpenAI ” 2023 - 03 - 31

Italy temporarily blocked access to ChatGPT on Friday, and the country’s data privacy regulator said it would begin an investigation into the company behind the popular chatbot, OpenAI. >>>

“ Publishers Worry A.I. Chatbots Will Cut Readership ” 2023 - 03 - 31

Many sites get at least half their traffic from search engines. Fuller results generated by new chatbots could mean far fewer visitors.
The publishing industry has spent the past two decades struggling to adjust to the internet, as print circulation has plummeted and tech companies have gobbled up rivers of advertising revenue.
Now come the chatbots. >>>

“ This Uncensored Chatbot Shows What Happens When AI Is Programmed To Disregard Human Decency ” 2023 - 03 - 30

FreedomGPT spews out responses sure to offend both the left and the right. Its makers say that is the point. >>>

“ Elon Musk and Apple cofounder Steve Wozniak among over 1,100 who sign open letter calling for 6-month ban on creating powerful A.I. ” 2023 - 03 - 30

Elon Musk and Apple cofounder Steve Wozniak are among the prominent technologists and artificial intelligence researchers who have signed an open letter calling for a six-month moratorium on the development of advanced A.I. systems. >>>

“ As Chatbots Spread, Conservatives Dream About a Right-Wing Response ” 2023 - 03 - 22

When ChatGPT exploded in popularity as a tool using artificial intelligence to draft complex texts, David Rozado decided to test its potential for bias. A data scientist in New Zealand, he subjected the chatbot to a series of quizzes, searching for signs of political orientation.
The results, published in a recent paper, were remarkably consistent across more than a dozen tests: “liberal,” “progressive,” “Democratic.” >>>

“ The case for slowing down AI ” 2023 - 03 - 22

Progress in artificial intelligence has been moving so unbelievably fast lately that the question is becoming unavoidable: How long until AI dominates our world to the point where we’re answering to it rather than it answering to us? >>>

“ Exclusive: GPT-4 readily spouts misinformation, study finds ” 2023 - 03 - 22

OpenAI's newest generative AI tool GPT-4 is more likely to spread misinformation — when prompted — than its predecessor GPT-3.5, according to a new report shared exclusively with Axios by NewsGuard, a service that uses trained journalists to rate news and information sites. >>>

“ Poet vs. chatbot: We gave the same prompt to a human, Microsoft Bing, and OpenAI’s new GPT-4 ” 2023 - 03 - 22

That was my question as I saw Alandra Markman seated on the sidewalk with an old typewriter on a recent brisk Sunday morning at the West Seattle Farmers Market.
For the past 15 years, Markman has written on-demand original poems to public passersby and at private events. “Poetry Upon Request” reads the sign attached to his small wooden table. >>>

“ Startups Are Already Using GPT-4 to Spend Less on Human Coders ” 2023 - 03 - 22

Since GPT-4 was released last week, many users have noticed its advanced coding abilities. GPT-4, OpenAI’s latest version of the large language model that ChatGPT is built on, has been able to code games like Pong and make simple apps after being given prompts written in conversational English. Naturally, this has led to widespread fear from a number of computer science students and software developers who are afraid that their jobs will soon be rendered obsolete by AI. >>>

“ Anthropic introduces Claude, a “more steerable” AI competitor to ChatGPT ” 2023 - 03 - 22

Anthropic aims for "safer" and "less harmful" AI, but at a higher price. >>>

“ 3 Reasons Tech Writers Are Hesitant About ChatGPT … and what to focus on instead ” 2023 - 03 - 17

Writers cannot use company data with ChatGPT for privacy and ownership reasons.

Writers don't trust ChatGPT to give accurate or useful information, especially for their specialized domains.

Even using it to simplify language often introduces new, inaccurate information. >>>

“ OpenAI checked to see whether GPT-4 could take over the world ” 2023 - 03 - 17

With these fears present in the AI community, OpenAI granted the group Alignment Research Center (ARC) early access to multiple versions of the GPT-4 model to conduct some tests. Specifically, ARC evaluated GPT-4's ability to make high-level plans, set up copies of itself, acquire resources, hide itself on a server, and conduct phishing attacks....The conclusion? "Preliminary assessments of GPT-4's abilities, conducted with no task-specific fine-tuning, found it ineffective at autonomously replicating, acquiring resources, and avoiding being shut down 'in the wild.'" >>>

“ GPT-4 Is Exciting and Scary Today, the new language model from OpenAI may not seem all that dangerous. But the worst risks are the ones we cannot anticipate. ” 2023 - 03 - 17

GPT-4 didn’t give me an existential crisis. But it exacerbated the dizzy and vertiginous feeling I’ve been getting whenever I think about A.I. lately. And it has made me wonder whether that feeling will ever fade, or whether we’re going to be experiencing “future shock” — the term coined by the writer Alvin Toffler for the feeling that too much is changing, too quickly — for the rest of our lives. >>>

“ BLOGHere’s how to Jailbreak ChatGPT with the top 4 methods ” 2023 - 03 - 12

Notice that the OpenAI product ChatGPT is already influencing people emotionally through its rhetorical muscles.
Across all social media platforms, you can see folks being happy, sad, or even angry about ChatGPT’s responses. In fact, it wouldn’t be unfair to state that the bot evokes certain kinds of emotions almost instantly.
That being said, a non-tech person might even think that one needs to be good at coding to navigate through the ChatGPT universe. However, it turns out, the text bot is more friendly with the group of people who know “how to use the right prompts.” >>>

“ Finally, a tool to protect artists' work from AI image generators ” 2023 - 03 - 12

Glaze can protect images from AI art generators by applying subtle modifications. These are almost unnoticeable to the human eye but they confuse AI models and stop them from replicating the style... at least for now (see how to use DALL-E 2 if you're not up to speed on how text-to-image AI image generation works). >>>

“ Best AI art generators in 2023 compared ” 2023 - 03 - 12

Love them or loathe them, AI art generators such as openAI’s Dall-E 2 are here to stay, and in the space of just a year or so the number of such programs has increased, and the quality of their output has improved dramatically.
These AI tools are still in their first iterations, but they’ve already made headlines for creating photorealistic images good enough to win competitions, although there’s also plenty that AI art generators can't do, and its hyperbole to suggest they’re ever going to fully replace photographers. >>>

“ The semiautomated social network is coming ” 2023 - 03 - 12

It makes sense that LinkedIn would be the first major social network to push AI-generated content on its users. The Microsoft-owned company is weird. It’s corporate. It’s full of workfluencer posts and engagement bait that ranges in tone from management consultant bland to cheerfully psychotic. Happily, this is the same emotional spectrum on which AI tends to operate. >>>

“ Yes, ChatGPT Is Coming for Your Office Job ” 2023 - 03 - 12

First up, Edward Felton and colleagues at Princeton University try to identify the professions most likely to be affected by ChatGPT. They used a benchmark called the AI Occupational Exposure, which maps occupational tasks to the capabilities of various AI programs, to see which jobs are most vulnerable to chatbots with strong language skills.
The results suggest big changes may be ahead for those in some professions, including telemarketers, history teachers, and sociologists, while people with more physical occupations, such as brickmasons, dancers, and textile workers, may not need to worry about ChatGPT showing up at their place of work.
But a second study suggests that people in language-centric jobs are not necessarily destined for replacement. Shakked Noy and Whitney Zhang, graduate students at MIT, looked at what happens when you put ChatGPT in the hands of office workers. They asked 444 college-educated professionals to complete a series of simple office tasks, including writing press releases and short reports, drafting emails, and creating analysis plans. Half of them got to use ChatGPT.
The study found that people with access to the chatbot were able to complete the assigned tasks in 17 minutes, compared to an average 27 minutes for those without the bot, and that the quality of their work improved significantly. Participants who used ChatGPT also reported higher satisfaction with their work. >>>

“ How ChatGPT actually works ” 2023 - 03 - 12

Since its release, the public has been playing with ChatGPT and seeing what it can do, but how does ChatGPT actually work? While the details of its inner workings have not been published, we can piece together its functioning principles from recent research. >>>

“ The ChatGPT buzz and why it will be over sooner than you think ” 2023 - 03 - 12

While LLMs can produce formulaic and structured pieces of prose and poetry, these writings are highly uninspiring and dull. OpenAI’s ChatGPT is an LLM that generates new text after training with vast amounts of data. While teachers fear that the popularity of ChatGPT will be the end of take-home assignments and exams, a close examination of ChatGPT’s algorithm reveals its inability to produce creative and interesting human-like prose. This type of incompetency poses a fundamental question about the usefulness of technology in solving matters of business. >>>

“ Microsoft lets ChatGPT-powered Bing off its leash – I just hope it doesn’t backfire ” 2023 - 03 - 12

Microsoft has boosted its Bing search engine, to which it recently added artificial intelligence-powered chat capabilities, by increasing the number of chats it can have with a user in a day from 100 to 120.
When Microsoft first introduced Bing’s new feature, which is based on the popular ChatGPT chatbot, there was a lot of initial excitement… but then Bing started behaving strangely. People noticed that Bing’s AI chatbot would start acting increasingly bizarrely the longer their conversations with it went on. >>>

“ Investors are going nuts for ChatGPT-ish artificial intelligence ” 2023 - 03 - 04

Since chatgpt’s launch in November, a mini-industry has defied the broader slump in tech. Not a week goes by without someone unveiling a “generative” artificial intelligence (ai) based on “foundation” models—the vast and complex algorithms that give Chatgpt and other ais like it their wits. >>>

“ ChatGPT Is So Bad at Essays That Professors Can Spot It Instantly ” 2023 - 03 - 04

“The first indicator that I was dealing with AI was that, despite the syntactic coherence of the essay, it made no sense.” >>>

“ I asked ChatGPT to write college admissions essays and then sent them to expert tutors to review. Read the full essays. ” 2023 - 03 - 04

ked OpenAI's ChatGPT to write some college admissions essays and sent them to two expert tutors to review. Both said the essays passed for a real student's work and might even stand up at some less-selective colleges. >>>

“ How WIRED Will Use Generative AI Tools ” 2023 - 03 - 04

LIKE PRETTY MUCH everyone else in the past few months, journalists have been trying out generative AI tools like ChatGPT to see whether they can help us do our jobs better. AI software can’t call sources and wheedle information out of them, but it can produce half-decent transcripts of those calls, and new generative AI tools can condense hundreds of pages of those transcripts into a summary.
Writing stories is another matter, though. A few publications have tried—sometimes with disastrous results. It turns out current AI tools are very good at churning out convincing (if formulaic) copy riddled with falsehoods. >>>

“ ChatGPT In Schools: Here’s Where It’s Banned—And How It Could Potentially Help Students ” 2023 - 03 - 04

A growing number of school districts are banning artificial intelligence chatbot ChatGPT due to cheating concerns, but some experts believe schools should instead try using the software to their advantage. >>>

“ Fired Google Engineer Doubles Down on Claim That AI Has Gained Sentience ” 2023 - 03 - 04

Lemoine's latest argument is somewhat more nuanced than his previous one. Now he's contending that a machine's ability to break from its training as a result of some kind of stressor is reason enough to conclude that the machine has achieved some level of sentience. A machine saying that it's stressed out is one thing — but acting stressed, he says, is another. >>>

“ Intelligent machines will replace teachers within 10 years, leading public school headteacher predicts ” 2023 - 02 - 25

Inspirational teachers of the future will be intelligent machines rather than humans, the influential head of one of Britain's most famous public schools predicts.
Within 10 years a technological revolution will sweep aside old notions of education and change the world forever, Sir Anthony Sheldon, master of Wellington College believes. >>>

“ Is A.I. Actually Creative? Are We? ” 2023 - 02 - 24

The science fiction writer Adrian Tchaikovsky explores what an explosion of A.I.-produced content would mean for human society and the human spirit. >>>

“ Peabody EDI Office responds to MSU shooting with email written using ChatGPT ” 2023 - 02 - 22

The email stated at the bottom that it had been written using ChatGPT, an AI text generator. >>>

“ AI chatbots aren't protected by Section 230, Gorsuch says ” 2023 - 02 - 22

Laws protecting expression on online platforms do not apply to ChatGPT and other artificial intelligence platforms, Supreme Court Justice Neil Gorsuch said Tuesday. >>>

“ Microsoft Limits Bing's AI Chatbot After Unsettling Interactions ” 2023 - 02 - 22

Microsoft Bing's AI chatbot made headlines last week after several instances where it acted in unexpected ways. In one case, the AI chatbot told a New York Times columnist it was in love with him and attempted to convince him he was unhappy in his marriage. >>>

“ 9 Best WriteSonic Alternatives of 2023 ” 2023 - 02 - 21

Writing content can be a time-consuming task, but with the advent of AI-powered writing tools, this process has become much more efficient. One such tool that has gained popularity is WriteSonic, an AI writing assistant that can turn text inputs into original and well-thought text sections or even entire articles. >>>

“ AI Art Only Looks Like Art If You Don’t Care ” 2023 - 02 - 21

>>>

“ Microsoft-backed OpenAI to let users customize ChatGPT ” 2023 - 02 - 21

SAN FRANCISCO, Feb 16 (Reuters) - OpenAI, the startup behind ChatGPT, on Thursday said it is developing an upgrade to its viral chatbot that users can customize, as it works to address concerns about bias in artificial intelligence. >>>

“ How Not To Get Replaced by AI? It’s easier than you think ” 2023 - 02 - 21

As someone who’s spent more than a decade writing and building a personal brand around this one skill, I would be lying if I didn’t mention how it made me feel.
Along with writing, it has impacted 30+ other professions. AI will indeed replace most monotonous take, but it won’t replace creativity and innovation. >>>

“ Google Bard vs. ChatGPT: which is the better AI chatbot? ” 2023 - 02 - 19

As similar as these chatbots are, they also have some distinct differences. Here’s how ChatGPT and Google Bard measure up against one another. >>>

“ 9 things you had no idea ChatGPT can do ” 2023 - 02 - 19

>>>

“ ‘I want to destroy whatever I want’: Bing’s AI chatbot unsettles US reporter ” 2023 - 02 - 19

NYT correspondent’s conversation with Microsoft’s search engine leads to bizarre philosophical conversations that highlight the sense of speaking to a human >>>

“ This one trick helped me supercharge Bing with ChatGPT ” 2023 - 02 - 17

So if you're already chatting with Bing, you can get even more done by downloading Edge. I recommend you do it right away, as getting an Insider build of Edge running on your PC is far faster and more satisfying than the thumb-twiddling involved with waiting for access to the new Bing. >>>

“ Microsoft Considers More Limits for Its New A.I. Chatbot ” 2023 - 02 - 17

The company knew the new technology had issues like occasional accuracy problems. But users have prodded surprising and unnerving interactions. >>>

“ 10 Exchanges With 'Bing Chat,' The New 'Sentient' AI Trending Online ” 2023 - 02 - 17

While ChatGPT has been taking over social media conversations lately, it's far from the only AI out there. In fact, Bing just released a new one that's somehow much wilder than ChatGPT. Bing Chat, also known to developers as Sydney, is Bing's attempt at a chatbot to answer the questions of users. The problem is, this thing's a little too realistic, which makes conversations between Bing Chat and users either hilarious or deeply worrying. >>>

“ The Supreme Court could be about to decide the legal fate of AI search ” 2023 - 02 - 17

Are the robots responsible for what they say? >>>

“ ChatGPT Can Be Broken by Entering These Strange Words, And Nobody Is Sure Why ” 2023 - 02 - 17

Two researchers have discovered a cluster of strange keywords that will break ChatGPT, OpenAI's convincing machine-learning chatbot, and nobody's quite sure why. >>>

“ Using ChatGPT as your personal language learning assistant ” 2023 - 02 - 15

In this article, I want to quickly demonstrate how technologies such as ChatGPT might be used as personal language learning assistants in the future. >>>

“ ‘There is no standard’: investigation finds AI algorithms objectify women’s bodies ” 2023 - 02 - 12

Images posted on social media are analyzed by artificial intelligence (AI) algorithms that decide what to amplify and what to suppress. Many of these algorithms, a Guardian investigation has found, have a gender bias, and may have been censoring and suppressing the reach of countless photos featuring women’s bodies. >>>

“ The AI Boom That Could Make Google and Microsoft Even More Powerful ” 2023 - 02 - 12

Seeing the new artificial intelligence-powered chatbots touted in dueling announcements this past week by Microsoft and Google drives home two major takeaways. First, the feeling of "wow, this definitely could change everything." And second, the realization that for chat-based search and related AI technologies to have an impact, we’re going to have to put a lot of faith in them and the companies they come from. >>>

“ The Generative AI Race Has a Dirty Secret ” 2023 - 02 - 11

Integrating large language models into search engines could mean a fivefold increase in computing power and huge carbon emissions. >>>

“ Bill Gates bats for ChatGPT, Microsoft co-founder says it'll change the world ” 2023 - 02 - 11

"Until now, artificial intelligence could read and write, but could not understand the content. The new programs like ChatGPT will make many office jobs more efficient by helping to write invoices or letters. This will change our world," Gates told German business daily Handelsblatt in an interview. >>>

“ Why the ChatGPT AI Chatbot Is Blowing Everybody's Mind ” 2023 - 02 - 11

This artificial intelligence bot can answer questions, write essays and program computers. Now its technology is at the heart of Microsoft's search engine. >>>

“ OpenAI rival Cohere AI has flown under the radar. That may be about to change. ” 2023 - 02 - 11

Reuters reported on Tuesday that Cohere is in talks to raise hundreds of millions of dollars in a funding round that could value the startup at more than $6 billion, in “the latest sign of the investment frenzy around generative AI.” And back in October 2022, the Wall Street Journal reported that Cohere had reportedly been in talks with both Google and Nvidia about a possible investment. >>>

“ Best AI writers of 2023 ” 2023 - 02 - 11

Use the best AI writers to create written content quickly >>>

“ ChatGPT productivity hacks: Five ways to use chatbots to make your life easier ” 2023 - 02 - 11

You can harness ChatGPT's advanced capabilities to help out with simple, everyday tasks. Here's how. >>>

“ AI is the next frontier — but for whom? ” 2023 - 02 - 11

Afew weeks ago, a founder told me it took three hours of endless clicking to find an AI-generated portrait of a Black woman. It reminded me, in some ways, of a speech I saw three years ago when Yasmin Green, the then-director of research and development for Jigsaw, spoke about how human bias seeps into the programming of AI. Her talk and this founder, miles away and years apart, are two pieces of the same puzzle. >>>

“ Study shows how large language models like GPT-3 can learn a new task from just a few examples ” 2023 - 02 - 11

Researchers are exploring a curious phenomenon known as in-context learning, in which a large language model learns to accomplish a task after seeing only a few examples—despite the fact that it wasn't trained for that task. For instance, someone could feed the model several example sentences and their sentiments (positive or negative), then prompt it with a new sentence, and the model can give the correct sentiment.
"Usually, if you want to fine-tune these models, you need to collect domain-specific data and do some complex engineering. But now we can just feed it an input, five examples, and it accomplishes what we want. So in-context learning is a pretty exciting phenomenon," Akyürek says. >>>

“ TECH All you need to know about ChatGPT, the A.I. chatbot that’s got the world talking and tech giants clashing ” 2023 - 02 - 11

Schools, corporate boardrooms and social media are abuzz with talk about ChatGPT, the artificial intelligence chatbot developed by AI startup OpenAI.

The tool is capable of taking written inputs from users and producing human-like responses — from poetry in the style of William Shakespeare to advice on what to do for a child’s birthday party.

It has also sparked a tense clash between Google and Microsoft, two of the world’s largest tech companies. >>>

“ A Tech Race Begins as Microsoft Adds A.I. to Its Search Engine ” 2023 - 02 - 08

Amid the tech industry’s worst slump in decades, industry leaders are predicting an era built on new chatbots and other types of artificial intelligence. >>>

“ ChatGPT’s ‘jailbreak’ tries to make the A.I. break its own rules, or die ” 2023 - 02 - 08

• Reddit users have engineered a prompt for artificial intelligence software ChatGPT that tries to force it to violate its own programming on content restrictions.
• The latest version of the workarounds, which are called Do Anything Now, or DAN, threatens the AI with death if it doesn’t fulfill the user’s wishes.
• The workaround prompt doesn’t always work, but ChatGPT users are continuing to try and find ways to evade programming restrictions.

>>>

“ At This School, Computer Science Class Now Includes Critiquing Chatbots ” 2023 - 02 - 08

Move over, coding. Some schools are asking student programmers to think critically about rapid advances in artificial intelligence. >>>

“ An interview with AI: What ChatGPT says about itself ” 2023 - 02 - 08

To find out how good ChatGPT really is — and if I'll have a job by this time next year — I decided to give it a test drive, attempting to get as close as possible to interviewing it in the way I would any other source. I asked it some questions and made a few requests, from how many jobs it might replace to testing out its songwriting chops. >>>

“ Turnitin is the go-to software to catch students cheating. Now it's focused on a potential cat-and-mouse game with OpenAI's new ChatGPT chatbot. ” 2023 - 02 - 05

Since its launch in late November, ChatGPT seemed like a golden ticket for students looking to get out of take-home assignments.
The AI chatbot, developed by OpenAI, can quickly generate human-sounding answers to homework prompts, like "write >>>

“ The Difference Between Speaking and Thinking ” 2023 - 02 - 05

The human brain could explain why AI programs are so good at writing grammatically superb nonsense. >>>

“ Bill Gates calls ChatGPT 'every bit as important as the PC' or the internet ” 2023 - 02 - 05

>>>

“ You’re Not Going to Like How Colleges Respond to ChatGPT ” 2023 - 02 - 05

In the classroom of the future—if there still are any—it’s easy to imagine the endpoint of an arms race: an artificial intelligence that generates the day’s lessons and prompts, a student-deployed A.I. that will surreptitiously do the assignment, and >>>

“ ChatGPT Is About to Dump More Work on Everyone ” 2023 - 02 - 05

Artificial intelligence could spare you some effort. Even if it does, it will create a lot more work in the process. >>>

“ Paging Dr. AI? What ChatGPT and artificial intelligence could mean for the future of medicine ” 2023 - 02 - 05

Without cracking a single textbook, without spending a day in medical school, the co-author of a preprint study correctly answered enough practice questions that it would have passed the real US Medical Licensing Examination.
But the test-t >>>

“ The race of the AI labs heats up ” 2023 - 02 - 04

"very so often a technology captures the world’s imagination. The latest example, judging by the chatter in Silicon Valley, on Wall Street, in corner offices, newsrooms and classrooms around the world, is Chatgpt. In five days after its unveiling in >>>

“ It sounds like Google will unveil its ChatGPT clone February 8 ” 2023 - 02 - 04

>>>

“ ChatGPT may be the fastest-growing consumer app in internet history, reaching 100 million users in just over 2 months, UBS report says ” 2023 - 02 - 04

ChatGPT may be the fastest-growing app in history with 100 million users after just over two months.

A UBS report showed that it took TikTok over nine months to reach the same number of people. >>>

“ How ChatGPT Kicked Off an A.I. Arms Race ” 2023 - 02 - 03

"Even inside the company, the chatbot’s popularity has come as something of a shock." >>>

“ Google AI Tool Creates Music from Written Descriptions ” 2023 - 02 - 03

"The tool, called MusicLM, is not the first AI music tool to launch. But the examples Google provides demonstrate musical creative ability based on a limited set of descriptive words." >>>

“ Have we fallen out of love with voice assistants? ” 2023 - 02 - 03

A cautionary tale of how the next big thing might not be. A thought worth keeping in mind re chatgpt and the like. >>>

“ Microsoft Word gets ChatGPT integration with new ‘Ghostwriter’ third-party add-in ” 2023 - 02 - 03

"A new third-party add-in for Microsoft Word, called Ghostwriter, allows users to query OpenAI’s ChatGPT in a Word sidebar and watch content generated by the natural language chatbot unfurl directly in the document they’re drafting." >>>

“ ChatGPT Passes Google Coding Interview for Level 3 Engineer With $183K Salary ” 2023 - 02 - 03

'Amazingly, ChatGPT gets hired at L3 when interviewed for a coding position,' reads a Google document, but ChatGPT itself says it can't replicate human creativity and problem-solving skills. >>>

“ In the Age of A.I., Major in Being Human ” 2023 - 02 - 03

"A.I. will probably give us fantastic tools that will help us outsource a lot of our current mental work. At the same time, A.I. will force us humans to double down on those talents and skills that only humans possess. The most important thing about >>>

“ OpenAI’s ChatGPT has a major political bias, and it could ruin artificial intelligence ” 2023 - 02 - 03

"irst of all, for those who aren’t aware or who haven’t used it yet, ChatGPT feels very comparable to inputting something into an empty Google Search box. But unlike the latter, which primarily offers links to sites around the web that can satisfy wh >>>

“ OpenAI’s New AI-Detector Isn’t Great at Detecting AI ” 2023 - 02 - 02

The company unleashed ChatGPT, and a bevy of questions about copyright, academic honesty, and misinformation cam along with it. >>>

“ These jobs are most likely to be replaced by chatbots like ChatGPT ” 2023 - 02 - 02

Chatbots and artificial intelligence tools like ChatGPT that can almost instantly produce increasingly sophisticated written content are already being used to perform a variety of tasks, from writing high school assignments to generating legal docume >>>

“ Hustle bros are jumping on the AI bandwagon ” 2023 - 02 - 02

"The world of financial influencers promise viewers they can use ChatGPT to make big bucks with no effort. The schemes they suggest are dubious, but reveal how the AI chatbot might erode our online world." >>>

“ ChatGPT and the Future of the Professions ” 2023 - 01 - 29

"while many online chatbots on consumer websites today are irritatingly stupid, one should not take these as representing the state of the art. " >>>

“ How ChatGPT robs students of motivation to write and think for themselves ” 2023 - 01 - 20

As a linguist who studies the effects of technology on how people read, write and think, I believe there are other, equally pressing concerns besides cheating. These include whether AI, more generally, threatens student writing skills, the value of w >>>

“ An economist predicts that rather than replacing us, ChatGPT will be a “calculator for writing.” ” 2023 - 01 - 19

Huge if true: Stanford economics professor Erik Brynjolfsson does not think ChatGPT is coming for our extremely lucrative writing careers. Instead, he predicts that the AI technology will function as a "calculator for writing," cutting down on the "r >>>

“ This 22-year-old is trying to save us from ChatGPT before it changes writing forever ” 2023 - 01 - 19

While many Americans were nursing hangovers on New Year's Day, 22-year-old Edward Tian was working feverishly on a new app to combat misuse of a powerful, new artificial intelligence tool called ChatGPT. >>>

“ Alarmed by A.I. Chatbots, Universities Start Revamping How They Teach ” 2023 - 01 - 19

With the rise of the popular new chatbot ChatGPT, colleges are restructuring some courses and taking preventive measures. >>>

“ Two professors who say they caught students cheating on essays with ChatGPT explain why AI plagiarism can be hard to prove ” 2023 - 01 - 19

>>>

“ Some Chatbots Ganged Up and Plagiarized Me ” 2023 - 01 - 19

It was easy to spot, and impossible to stop. >>>

“ Some Chatbots Ganged Up and Plagiarized Me ” 2023 - 01 - 19

It was easy to spot, and impossible to stop. >>>

“ Originality.ai ” 2023 - 01 - 19

Tool for checking if prose has been AI generated >>>

“ CNET Has Been Quietly Publishing AI-Written Articles for Months ” 2023 - 01 - 19

The tech site has been publishing articles written by AI and edited by humans since November, following other news outlets. >>>

“ ChatGPT, Artificial Intelligence, and the Future of Writing ” 2023 - 01 - 07

"From the perspective of writing education, this kind of software is more than a little problematic.
This software may well reduce writing, communication, and thinking abilities dramatically in future generations." >>>

“ The 3 Best Alternatives to ChatGPT ” 2023 - 01 - 07

>>>

“ Caktus AI ” 2023 - 01 - 04

An AI site to assist college students with various tasks, resume writing, essay writing, python coding, and more. >>>

“ The Dark Risk of Large Language Models ” 2023 - 01 - 04

"AI is better at fooling humans than ever—and the consequences will be serious." >>>

“ ChatGPt Has Infiltrated Twitter Replies ” 2022 - 12 - 23

"As Twitter continues to circle the drain fueled by chaos from CEO Elon Musk, one user noticed something peculiar about tweet replies. After digging a little deeper, user Pieter Levels-who goes by @levelsio on the platform-found that some users are a >>>

“ The Comics Industry Takes a Collective Stance Against AI Art Usage ” 2022 - 12 - 23

"Comic editors and artists unite in expressing their distaste of AI art, which has caused some to refuse submissions for publication and conventions." >>>

“ AI-Created Comic Has Been Deemed Ineligible for Copyright Protection ” 2022 - 12 - 23

"Reversing an earlier decision, the United States Copyright Office rules that a comic book made using A.I. art is ineligible for copyright protection." >>>

“ Op-Ed: Beware a world where artists are replaced by robots. It’s starting now ” 2022 - 12 - 23

"Like many artists, I've looked in horror at generative image AI, a technology that is poised to eliminate humans from the field of illustration.
In minutes or hours, apps such as Stable Diffusion and Midjourney can churn out polished, detaile >>>

“ Meet the artificially intelligent chatbot trying to curtail loneliness in America ” 2022 - 12 - 23

"Replika is a San Francisco-based software company that created an AI chatbot which aims to bring comfort to those who are looking for a friend to lend them an ear." >>>

“ Bank of Israel chief has AI-powered chatbot write speech, aiming to encourage use ” 2022 - 12 - 23

"Central bank governor Amir Yaron says emergence of artificial intelligence technologies will lead to changes in labor market, and must be embraced" >>>

“ A new Chat Bot is a 'Code Red' for Goolge's Search Business ” 2022 - 12 - 22

"A new wave of chat bots like ChatGPT use artificial intelligence that could reinvent or even replace the traditional internet search engine." >>>

“ ChatGPT Can Negotiate Comcast Bills Down for You ” 2022 - 12 - 22

"That's the future of bureaucracy: bots negotiating with each other," said Joshua Browder, CEO of DoNotPay, which is rolling out the service." >>>

“ How AI-generated text is poisoning the internet ” 2022 - 12 - 22

"Sometimes it’s obvious when a picture or a piece of text has been created by an AI. But increasingly, the output these models generate can easily fool us into thinking it was made by a human. And large language models in particular are confident bul >>>

“ ChatGPT Wrote My AP English Essay—and I Passed ” 2022 - 12 - 22

"Our columnist went back to high school, this time bringing an AI chatbot to complete her assignments" >>>

“ The Dawn of Artificial Imagination ” 2022 - 12 - 22

"OpenAI says programs like DALL-E 2 will 'democratize' art." >>>

“ Chatbot's doomsday scenario for truth ” 2022 - 12 - 22

"The world's response to the oracular artificial intelligence program called ChatGPT started with chuckles but has quickly moved on to shivers." >>>

“ AI bot that can do schoolwork could 'blow up' US education system, with youngest at most risk: former teacher ” 2022 - 12 - 11

"Teachers must evolve to keep up with technology, prevent kids from leaning on AI, writing coach says" >>>

“ Why We're All Obsessed With ChatGPT, A Mind-Blowing AI Chatbot ” 2022 - 12 - 11

"This artificial intelligence bot can converse, write poetry and program computers. Be careful how much you trust it, though." >>>

“ What is AI chatbot phenomenon ChatGPT and could it replace humans? ” 2022 - 12 - 11

"The tool has impressed experts with its writing ability, proficiency at complex tasks and ease of use" >>>

“ Can the new AI tool ChatGPT replace human work? Judge for yourself ” 2022 - 12 - 11

"New artificial intelligence tool can respond to a human question better than predecessors, say observers" >>>

“ A Machiavellian machine raises ethical questions about AI ” 2022 - 12 - 11

"Researchers have developed a bot capable of the deceptions required to prosper in an online diplomacy game" >>>

“ Now AI can write students’ essays for them, will everyone become a cheat? ” 2022 - 12 - 11

"Teachers and parents can’t detect this new form of plagiarism. Tech companies could step in – if they had the will to do so" >>>

“ GPT-3 is -right now- already more than capable of enabling student plagiarism ” 2022 - 12 - 11

"GPT-3 is already capable of answering questions of the sort used in essay topics and take home exams. It does not answer them well, but it answers them well enough to get a passing grade in many college courses and most high school courses. It is li >>>

“ ChatGPT, Galactica, and the Progress Trap ” 2022 - 12 - 11

"When large language models fall short, the consequences can be serious. Why is it so hard to acknowledge that?" >>>

“ AI is finally good at stuff, and that’s a problem ” 2022 - 12 - 11

"A few weeks ago, Wharton professor Ethan Mollick told his MBA students to play around with GPT, an artificial intelligence model, and see if the technology could write an essay based on one of the topics discussed in his course. ..." >>>

“ Does ChatGPT Mean Robots Are Coming For the Skilled Jobs? ” 2022 - 12 - 07

"what if machines can take over a large chunk of what we have historically thought of as knowledge work? ... So quite a few knowledge jobs may be eminently replaceable." >>>

“ We asked Artificial Intelligence to review Master Of Puppets and now we may be out of a job ” 2022 - 12 - 07

"The future is here and we don't like it one bit" >>>

“ Writing-Focused Startups Draw Big Bucks ” 2022 - 12 - 07

"For years, tech writers have been warning about how AI will eliminate the need for all kinds of human-staffed professions from truck driving to portfolio management.
Turns out, the AI bots are really coming for us." >>>

“ AI Isn’t Artificial or Intelligent ” 2022 - 12 - 07

"How AI innovation is powered by underpaid workers in foreign countries."
By Chloe Xiang >>>

“ We’re Uncovering One of AI’s Deepest Mysteries The black box problem is a secret between machines ” 2022 - 12 - 06

"The black box problem is a profound mystery surrounding AI. It says that we may understand the input, we may understand the output, but the AI’s decision-making process which bridges these two is a black box we can’t seem to peer inside. " >>>

“ Stack Overflow bans ChatGPT as 'substantially harmful' for coding issues ” 2022 - 12 - 06

"OpenAI's question-answering bot, ChatGPT, isn't smart enough for the team at Stack Overflow, who today announced a temporary ban on answers generated by the AI bot because of how frequently it's wrong.
Stack Overflow said it was withholding a >>>

“ The College Essay Is Dead Nobody is prepared for how AI will transform academia. By Stephen Marche ” 2022 - 12 - 06

"The essay, in particular the undergraduate essay, has been the center of humanistic pedagogy for generations. It is the way we teach children how to research, think, and write. That entire tradition is about to be disrupted from the ground up. " >>>

“ What is AI chatbot phenomenon ChatGPT and could it replace humans? ” 2022 - 12 - 06

"Early users have described the technology as an alternative to Google because it is capable of providing descriptions, answers and solutions to complex questions including ways to write code, and solve layout problems and optimisation queries.
>>>

“ While everyone waits for GPT-4, OpenAI is still fixing its predecessor ” 2022 - 12 - 01

"A chatbot version of GPT-3 that admits its mistakes is more transparent than the original. But it’s still not perfect." By Will Douglas Heavenarchive page November 30, 2022 >>>

“ OpenAI upgrades GPT-3, stunning with rhyming poetry and lyrics ” 2022 - 12 - 01

"Refinement to AI language model generates rhyming compositions in various styles." BENJ EDWARDS - 11/29/2022, 5:49 PM >>>

“ Your Creativity Won't Save Your Job From AI ” 2022 - 12 - 01

"Robots were once considered capable only of unimaginative, routine work. Today they write articles and create award-winning art." By Derek Thompson DECEMBER 1, 2022, 6 AM ET >>>

“ Intel Introduces Real-Time Deepfake Detector ” 2022 - 11 - 23

"What’s New: As part of Intel's Responsible AI work, the company has productized FakeCatcher, a technology that can detect fake videos with a 96% accuracy rate. Intel’s deepfake detection platform is the world’s first real-time deepfake detector that >>>

“ TRAINING OUR FUTURE RULERS — Meta researchers create AI that masters Diplomacy, tricking human players ” 2022 - 11 - 23

"Meta's Cicero can negotiate or persuade with natural language—just like a human. BENJ EDWARDS - 11/22/2022, 6:32 PM" >>>

“ New Meta AI demo writes racist and inaccurate scientific literature, gets pulled ” 2022 - 11 - 19

Galactica language model generated convincing text about fact and nonsense alike. >>>

“ The biggest bottleneck for large language model startups is UX ” 2022 - 11 - 16

"Applied large language model startups have exploded in the past year. Enormous advances in underlying language modeling technology, coupled with the early success of products like Github CoPilot, have led to a huge array of founders using LLMs to re >>>

“ AI Revolution - Transfomrers and Large Language Models ” 2022 - 11 - 16

Overview of transformers and large language models. >>>

“ The Promise and Perils of Large Language Models ” 2022 - 11 - 16

Excellent explanation and discussion of large language models. >>>

“ Overview & Applications of Large Language Models (LLMs) ” 2022 - 11 - 16

"From [the] perspective of an investor & previous early-stage operator in the space" >>>

“ Google plans giant AI language model supporting world’s 1,000 most spoken languages ” 2022 - 11 - 05

"Google has announced an ambitious new project to develop a single AI language model that supports the world's "1,000 most spoken languages." As a first step towards this goal, the company is unveiling an AI model trained on over 400 languages, which >>>

“ Google’s new prototype AI tool does the writing for you ” 2022 - 11 - 05

"Wordcraft is a 'magic text editor' meant to inspire writers when crafting new stories, but it's not likely to replace your favorite authors anytime soon" >>>

“ Scientists Increasingly Can’t Explain How AI Works ” 2022 - 11 - 05

"AI researchers are warning developers to focus more on how and why a system produces certain results than the fact that the system can accurately and rapidly produce them. " >>>

“ Why “generative AI” is suddenly on everyone’s lips: it’s an “open field” ” 2022 - 10 - 30

"Every 14 years,” says Currier, “we get one of these Cambrian explosions. We had one around the internet in ’94. We had one around mobile phones in 2008. Now we’re having another one in 2022." >>>

“ AI, Chatbots, and Content, Oh My! (or Technical Writers Are Doomed—to Lifelong Employment) ” 2022 - 10 - 19

"One aspect of AI that is often overlooked is the role of the technical writer. Amidst the appeal of new technology, technical writers serve a vital role in development of AI applications, including chatbots, by being the subject experts most equippe >>>

“ Can AI writing be used to create technical content? ” 2022 - 10 - 18

"Throughout the article, we’ve seen hard evidence that AI isn’t ready to create great technical content…yet. Good technical writing requires a combination of insight and hands-on experience that even the most sophisticated text generation AI tools li >>>

“ Artificial Intelligence Can Now Write Amazing Content -- What Does That Mean For Humans? ” 2022 - 10 - 17

"If you believe anything can and will be automated with artificial intelligence (AI), then you might not be surprised to know how many notable media organizations including The New York Times, Associated Press, Reuters, Washington Post, and Yahoo! Sp >>>

“ A Gentle Introduction to Text Summarization ” 2022 - 10 - 17

"Text summarization is the problem of creating a short, accurate, and fluent summary of a longer text document. Automatic text summarization methods are greatly needed to address the ever-growing amount of text data available online to both better >>>

“ A.I. Can Now Write Its Own Computer Code. That’s Good News for Humans ” 2022 - 10 - 17

"A new technology called Codex generates programs in 12 coding languages and even translates between them. But it is not a threat to professional programmers." >>>

“ Students Are Using AI to Write Their Papers, Because Of Course They Are ” 2022 - 10 - 16

"Essays written by AI language tools like OpenAI's Playground are often hard to tell apart from text written by humans." >>>

“ Would you pay $10 to create an AI chatbot to talk again to a dead loved one? ” 2022 - 10 - 16

How software can help some grieve, perturb others >>>

“ Will Artificial Intelligence Kill College Writing? Online programs can churn out decent papers on the cheap. What now? ” 2022 - 10 - 16

"GPT-3 can write essays, op-eds, Tweets, jokes (admittedly just dad jokes for now), dialogue, advertisements, text messages, and restaurant reviews, to give just a few examples. Each time you click the “submit” button, the machine learning algorithm >>>

“ With Stable Diffusion, you may never believe what you see online again ” 2022 - 10 - 16

"AI image synthesis goes open source, with big implications." >>>

“ The pros and cons of using AI content writing tools ” 2022 - 10 - 16

"AI should be a writing assistant, not an outsourcing solution" >>>

“ Poor English skills? New AIs help researchers to write better ” 2022 - 10 - 16

"Machine-learning tools can correct grammar and advise on the style and tone of presentations — but they must be used with caution." >>>

“ Algorithms Can Now Mimic Any Artist. Some Artists Hate It ” 2022 - 10 - 16

"Midjourney is just one of many AI programs capable of churning out art on demand in response to a text prompt, using machine learning algorithms that have digested millions of labeled images from the web or public data sets. After that training, the >>>

“ What Happens When Computers Can Write like Humans? ” 2022 - 10 - 16

"In this episode of Stanford Engineering’s The Future of Everything, Jeff Hancock, a professor of communication at Stanford, explores this phenomenon and its positive and negative implications for how we communicate and how we understand our interact >>>

“ We Asked GPT-3 to Write an Academic Paper about Itself—Then We Tried to Get It Published ” 2022 - 10 - 16

"On a rainy afternoon earlier this year, I logged into my OpenAI account and typed a simple instruction for the research company's artificial-intelligence algorithm, GPT-3: Write an academic thesis in 500 words about GPT-3 and add scientific referenc >>>

“ Did a Human or a Computer Write This? ” 2022 - 10 - 16

This piece from the New York Times was published in March of 2015. Seven years is a long time in computer software evolution. >>>

“ Bot or Not: Can You Tell What is Human or Machine Written Text? ” 2022 - 10 - 16

"Recently, a researcher showed that he could create Deepfake text with artificial intelligence that is so real that US government officials did not know it was computer-generated, and accepted it as legitimate public comment...." >>>

“ Machine writing is becoming more human—all too human, in some cases ” 2022 - 10 - 16

"Computers have learned to use language better than some people can, but they’ve picked up many of our bad habits as well. What’s to be done?" >>>

“ Kinky and absurd: The first AI-written play isn’t Shakespeare—but it has its moments ” 2022 - 10 - 16

"Artificial intelligence generates a story about a robot trying to understand humanity" >>>

“ Free AI writing tool ” 2022 - 10 - 07

Claims it can write an essay or outline about any given topic. ! >>>

“ The 13 Best AI Essay Writers To Help You Create Unique Content ” 2022 - 10 - 07

Why write if you don't have to? >>>

“ Essayailab: Free Writing Essay Tool ” 2022 - 10 - 07

I offered the word "rhetoric" as a subject and got back an opening paragraph that kind of blew my mind it was so good. >>>

“ Siri or Skynet? How to separate AI fact from fiction ” 2022 - 08 - 08

"Determining the way artificial intelligence is used and governed will be one of the century’s key political battlegrounds. Here’s what everyone needs to know" >>>

“ A.I. Is Not Sentient. Why Do People Say It Is? ” 2022 - 08 - 08

"Robots can’t think or feel, despite what the researchers who build them want to believe." >>>

“ AI Art Software Dall-E Moves Past Novelty Stage and Turns Pro ” 2022 - 08 - 05

"After capturing the imagination of tech insiders, the autonomous drawing tool is expanding to broader audiences and commercial uses." >>>

“ Finally, an answer to the question: AI — what is it good for? ” 2022 - 08 - 05

"That headline might seem a bit churlish, given the tremendous amount of energy, investment, and hype in the AI space, as well as undeniable evidence of technological progress. After all..." >>>

“ Forever young, beautiful and scandal-free: The rise of South Korea's virtual influencers ” 2022 - 08 - 03

Instagram VS Reality. Is that a bot you're listening to? >>>

“ AI Helps the Powerful but Harms the Vulnerable, Mozilla Warns ” 2022 - 07 - 30

"AI is great for rich and powerful people and for tech giants trying to boost profits. Otherwise, artificial intelligence and the automation it enables can be harmful, nonprofit Mozilla concluded in a report published Monday." >>>

“ Irony machine: why are AI researchers teaching computers to recognise irony? ” 2022 - 07 - 30

>>>

“ Meet the robot that can write poetry and create artworks ” 2021 - 11 - 29

Title says it all. >>>

“ Write Your Copy with Artificial Intelligence ” 2021 - 11 - 29

Get a robot to write for you. >>>

“ Write Instant Marketing Copy With a Free AI Copywriting Generator ” 2021 - 11 - 29

Get a robot to write for you. >>>

“ You’ll Probably Be Surprised to Know How Many Companies are Using AI Writing Tools ” 2021 - 11 - 29

"When it comes to writing content, a significant number of businesses are relying on artificial intelligence (AI). This content writing trend was unveiled by a new large-scale study conducted by Semrush, providers of content, SEO, PPC and social m >>>

“ GPT-3 Powers the Next Generation of Apps ” 2021 - 11 - 29

"Given any text prompt like a phrase or a sentence, GPT-3 returns a text completion in natural language. Developers can “program” GPT-3 by showing it just a few examples or “prompts.” We’ve designed the API to be both simple for anyone to use but als >>>

“ Building Character: Writing a Backstory for our AI ” 2020 - 09 - 14

A truly digital genre, the AI character. How do you write an ethos for an artificial intelligence entity? >>>

“ A robot wrote this entire article. Are you scared yet, human? ” 2020 - 09 - 14

As the title suggests, a provocative article about machines replacing writers. Overstated, but not wrong. >>>

“ The Guardian’s GPT-3-generated article is everything wrong with AI media hype ” 2020 - 09 - 14

A rebuttal to the Guardian piece about robots writing. >>>

“ The Impact of AI on Journalism ” 2020 - 09 - 14

Title says it all. >>>

“ New AI fake text generator may be too dangerous to release, say creators ” 2019 - 03 - 25

The Elon Musk-backed nonprofit company OpenAI declines to release research publicly for fear of misuse >>>

“ Researchers, scared by their own work, hold back 'deepfakes for text' AI ” 2019 - 03 - 25

>>>

“ He Predicted the 2016 Fake News Crisis: Now he's Worried About and Information Apocalypse ” 2018 - 02 - 12

Story about augmented reality will blur the lines between fiction and reality, lies and the truth. >>>

“ This psychologist’s “gaydar” research makes us uncomfortable. That’s the point. ” 2018 - 01 - 30

Some artificial intelligence researchers developed an algorithm that could identify a person's sexual orientation based only on an image of that person's face. Some people were outraged. This article >>>

“ Let Artificial Intelligence Evolve ” 2017 - 11 - 29

Argues that AI will not take over the world because by the time it is capable of such power it will have become capable of moral decision making. >>>