Generative AI (GPT) in Higher Ed

Ray Schroeder, UPCEA Senior Fellow

This site was originally developed for the EDUCAUSE Quick Talk on 1/30/23.  I have continued to update and revise the site to keep the site current for presentations.  Included are some discussion starters in red bold.  This is designed as a resource to be used in whole or in part by readers to lead discussions among their admnistrators, faculty, students, peers and others as we enter this new phase of AI-enhanced higher education.  

There are so many developments in gen AI that I found it difficult to format this into an easily navigated site.  Until I can organize this site, I recommend that you simply browse the site or - if you are looking for a particular topic - use the search page "find" tool - ctl-F - in most browsers, to do keyword searches for the topic you are seeking.

Other Presentation Sites:

Presentation to University of New Hampshire Faculty Instructional Technology and Strategies Institute   (FITSI)

Presentation to faculty on Generative AI Search

 Presentation to UPCEA Annual Conference 3/23/2023


"The single biggest thing we are ever going to see in our lifetime..." -Sebastian Thrun 

(Can you suggest something else of this sort that has or will touch nearly every industry, business, career?)

Udacity CEO and Co-founder, Stanford Professor Sebastian Thrun joins Becky Anderson on CNN International and shares his thoughts on the impacts of AI and what that means for the future of education.

23Amazing, Astounding, Thought-Inducing - If you have 15 minutes please read this from OpenAI - Ray Schroeder, UPCEA Sr Fellow

My friends, I have never before reached out to you personally to read a report - but read this. [message I sent out on 3/16/23 - in decades of sharing such reports - I have not read anything that matches the impact and potential in this report and accompanying materials]

I asked ChatGPT is generative AI a disruptive innovation for higher education?  

Its first response to me 10 seconds later on 2/16/23:


Generative AI has the potential to be a disruptive innovation for higher education in several ways. However, it is important to note that the extent of its impact will depend on how it is developed and implemented.

One way generative AI could disrupt higher education is by automating certain aspects of the learning process. For example, AI-powered chatbots could assist students with answering their questions, grading assignments, or even designing personalized curricula based on their individual learning style. This could potentially reduce the need for human instructors and support staff, leading to significant cost savings for educational institutions.

Another potential application of generative AI in higher education is through the creation of intelligent tutoring systems. These systems could use AI algorithms to analyze a student's learning progress and provide personalized feedback and guidance. This could potentially improve the effectiveness of education and help students learn at their own pace.

However, it is important to note that the use of generative AI in higher education also poses significant challenges and ethical concerns. For example, there are concerns around data privacy, bias, and transparency in the algorithms used in AI systems. There is also the risk that the use of AI could lead to a reduction in the quality of education if it is not implemented properly.

In summary, generative AI has the potential to be a disruptive innovation for higher education, but its impact will depend on how it is developed and implemented, and how educational institutions navigate the ethical and practical challenges that come with its use.

AI Transforming Education - Ray Schroeder, Inside Higher Ed

The era of AI management of big data is upon us. Even in the slow-moving field of education, big data is making a difference. Identifying trends that never before had been uncovered and using predictive analytics to generate models of the future are commonplace in all aspects of higher ed including tracking and predicting enrollment demographics. Much more of the text generated in our field than many realize is actually written by—or inspired by—AI! 

Sports reports, press releases and annual reports use AI in a variety of ways. GPT-3, the third-generation Generative Pre-trained Transformer, is a neural network machine learning model trained using internet data to generate any type of text. Developed by OpenAI, it requires only a small amount of input text to generate sophisticated machine-generated text.

In the Coming Weeks, How to Respond to Generative AI - Ray Schroeder, Inside Higher Ed

(Given that generative AI is a virtual teenager, learning and improving week-by-week with  a growing massive memory, developing writing aptitude, and ingenious creativity, how can we mere mortals compete for our jobs against AI?

What can we expect? Some technological improvements will be noticeable by next month, as GPT-4 is scheduled to be released. Those improvements will certainly be impressive. Faster, smoother, fewer lapses and multimodal models are expected to emerge with GPT-4. All the while, the algorithms will get smarter, with ever-larger knowledge bases and even more than the 175 billion parameters of GPT-3. Equally impressive will be the variety of applications and interfaces that emerge. These will be accelerated in part by the race between Microsoft/OpenAI and Alphabet/Google with a variety of emerging applications. One important aspect of the emergence of generative AI that has not received enough attention for those of us in higher education is that the output of these systems is not subject to copyright.

Should educators worry about ChatGPT? -  JODI HECKEL, Illinois 4/5/2023

Some students are using models to help write their papers and do homework, and yes, that is something to worry about. We want students to learn, and if they’re just pasting an assignment into a box and hitting return, they’re not learning much.  But that’s a small part of a bigger issue, which is that the students now entering college are likely to graduate into a world transformed by artificial intelligence. Models like ChatGPT are already being integrated into word processing software and search engines. In 10 years, they will be as familiar as autocomplete is to us now. So, telling students “just say no to AI” is not going to be a sufficient way to prepare them for the 2030s. Students will be using these models, and will need to understand them.

How to handle AI chatbots in the classroom - Megan Hart, Journal of Accountancy (5/10/2023)

Some teachers have embraced the generative pre-trained transformer (GPT) technology and incorporate it in their classrooms. Others approach ChatGPT and its successor, GPT-4, with concern that students will use these tools to cheat or to bypass tasks that would help them develop critical thinking skills. During the forum, faculty discussed what an AI chatbot can and can't do, as well as ways to use it appropriately in the classroom. Also discussed was how to discourage students from cutting and pasting ChatGPT answers instead of creating their own.

First, some definitions:

Deconstructing ChatGPT on the Future of Continuing Education - Ray Schroeder, Inside Higher Ed

(Can GPT Mentor?  Can GPT auto-generate certificates and validate via assessments?)

Released on Nov. 30, ChatGPT and GPT-3.5 were publicly unveiled by OpenAI—a leader in generative artificial intelligence. I wondered what this release might mean for the future of continuing higher education. Of course, nothing had yet been written about the potential of this just-released version, so I asked ChatGPT to write a short poem about it. In just three seconds, far faster than I could have typed the words, the poem was complete on my screen. Let’s deconstruct the poem and look closely at what ChatGPT has referenced.

Has AI reached the point where a software program can do better work than you? - Rob Schmitz talks to Ethan Mollick, NPR Morning Edition

(Is your job in jeopardy today... next year?  What are the uniquely human aspects of careers that are unlikely to be replicated in a more cost-effective, and efficient way than AI?  Hint - Ask GPT)

I mean, there's a few things, right? So the most obvious thing and the thing people come away with if they play with ChatGPT for just a few minutes is, wow, I can cheat on essays with this thing. And then if they spend a couple more minutes, they say, well, I can cheat on creating software code or translating language. But the uses actually go way beyond that, and I've been amazed by what some of my students have been reporting about how they're using the capabilities. 

A Survey of 31,000 Employees Shows 49 Percent Fear A.I. Will Steal Their Jobs. They're Right to Worry - Minda Zetlin, Inc. (5/19/2023)

Almost half of employees--49 percent--fear they will lose their jobs to A.I., according to a new survey commissioned by Microsoft. At the same time, 70 percent hope that A.I. will help them manage their ever-growing workloads instead. It's clear from these numbers that many people see A.I. as both a benefit and a threat. This oddly contradictory view of artificial intelligence is somehow a perfect symbol of its place in our imaginations at this moment in history--something that will eliminate countless jobs, boost creativity, and put an end to drudgery, or perhaps a monstrous force that will take over our planet and enslave humanity.

GPT in Higher Education - Ray Schroeder, Inside Higher Ed

(Will generative AI be ignored or rejected - why, how, when?  Instead, is it likely to grow to the extent that it saves money and provides a faster product?  Check out Clayton Christensen's Disruptive Innovation Theory - is this a classic example?)

It has become clear that advances in technology are rarely, if ever, denied by society. I am confident that generative AI will be embraced by business and industry in ways that will enhance efficiency and accuracy in services. So, our learners, as they pursue careers, will do so in an AI-rich environment. They will be expected to make the best use of these technologies to perform effectively on the job. Thus, it is incumbent on us, as educators, to ensure that our learners have experience with the technologies as well as develop effective practices for their optimal use.

OpenAI announces GPT-4, claims it can beat 90% of humans on the SAT - Kif Leswing, CNBC

(So this is the intellectual level of your new assistant - 93rd percentile on SAT ... and improving)

OpenAI announced the latest version of its primary large language model, GPT-4, on Tuesday, that it says exhibits “human-level performance” on many professional tests. GPT-4 performed at the 90th percentile on a simulated bar exam, the 93rd percentile on an SAT reading exam, and the 89th percentile on the SAT Math exam, OpenAI claimed.

5 ways GPT-4 outsmarts ChatGPT - Devin Coldewey, Tech Crunch

OpenAI’s new GPT-4 AI model has made its big debut and is already powering everything from a virtual volunteer for the visually impaired to an improved language learning bot in Duolingo. But what sets GPT-4 apart from previous versions like ChatGPT and GPT-3.5? Here are the five biggest differences between these popular systems.  1. GPT-4 can see and understand images.  GPT-4, however, can be given images and it will process them to find relevant information. You could simply ask it to describe what’s in a picture, of course, but more importantly its understanding goes beyond that.

OpenAI, the company behind ChatGPT, in talks for tender offer that would give it $29 billion valuation: report - Bill Peters, MarketWatch

(They built GPT 3.5 with three billion $$; what can we expect with three times that funding?)

Artificial-intelligence research company OpenAI is in discussions over potentially selling at least $300 million in shares in a tender offer that would give it a roughly $29 billion valuation, the Wall Street Journal reported Thursday. The offering of shares of OpenAI — known for AI programs like the chatbot ChatGPT and the image-generator Dall-E 2 — would make it among the most highly-valued startups in the U.S., the Journal said. The valuation would be more than twice its valuation of $14 billion in 2021, according to the Journal.

Microsoft and OpenAI announce Multi-year, Muli-billion dollar partnership extension

(Where will this put Microsoft and Bing vis-a-vis Alphabet and Google?)

This multi-year, multi-billion dollar investment from Microsoft follows their previous investments in 2019 and 2021, and will allow us to continue our independent research and develop AI that is increasingly safe, useful, and powerful. In pursuit of our mission to ensure advanced AI benefits all of humanity, OpenAI remains a capped-profit company and is governed by the OpenAI non-profit. This structure allows us to raise the capital we need to fulfill our mission without sacrificing our core beliefs about broadly sharing benefits and the need to prioritize safety.

ChatGPT firm trials $20 monthly subscription fee - Zoe Kleinman, BBC

(Would this be worth $240 a year to you and your unit? ChatGPT-Plus:  I thought so and signed-up!  :-)

For $20 (£16) per month, subscribers will get access to the platform even at peak times when it can be hard to log onto, and also "priority access" to new features, chatbot creator OpenAI said. It plans to extend the trial more widely but initially it will only be offered to those on a waiting list. The free version will still be available, the firm said.

ChatGPT vs. Bing Chat: Which AI chatbot should you use? - Sabrina Ortiz, ZD Net (3/24/2023)

(Here the two flavors of GPT from OpenAI are described - they have different features for different uses!)

In February, Microsoft announced its integration of ChatGPT to its Bing search engine called Bing Chat. This chatbot has some major differences from ChatGPT, with the biggest difference being access to the entirety of the internet. So which chatbot should you reach for your AI needs? We compared ChatGPT (the free version) and Bing Chat to help you make your decision easier.

OpenAI CEO: Multi-Modal ChatGPT 4 coming soon - Roger Montti, Search Engine Journal

(This seems to include chats, video, images, news, maps and more - see for a working example of one "multimodal" generative AI)

OpenAI CEO Sam Altman says don't expect an Artificial General Intelligence (AGI).  An AI with multimodal capabilities can interact through speech. It can listen to commands and provide information or perform a task. Altman offered these tantalizing details about what to expect soon: “I think we’ll get multimodal models in not that much longer, and that’ll open up new things. I think people are doing amazing work with agents that can use computers to do things for you, use programs and this idea of a language interface where you say a natural language – what you want in this kind of dialogue back and forth. You can iterate and refine it, and the computer just does it for you. You see some of this with DALL-E and CoPilot in very early ways.”

"Did I Mention this Content Infrastructure Will Be Open?"

(This from the co-founder of Lumen Learning - what does this mean to the future of OER and copyrights?)

 Excerpted from AI, Instructional Design, and OER - David Wiley, Open Content

In his application to register a work he created using AI software like Stable Diffusion, Steven Thaler wrote that the work “was autonomously created by a computer algorithm running on a machine” and that he was “seeking to register this computer-generated work as a work-for-hire to the owner.” In other words, he applied for copyright protection for a work he created by providing a prompt to a generative AI tool. The US Copyright Office rejected his attempt to register copyright in the work – twice. In their final response they wrote:

Copyright law only protects “the fruits of intellectual labor” that “are founded in the creative powers of the [human] mind.” COMPENDIUM (THIRD) § 306 (quoting Trade-Mark Cases, 100 U.S. 82, 94 (1879)); see also COMPENDIUM (THIRD) § 313.2 (the Office will not register works “produced by a machine or mere mechanical process” that operates “without any creative input or intervention from a human author” because, under the statute, “a work must be created by a human being”)….

While the [review] Board is not aware of a United States court that has considered whether artificial intelligence can be the author for copyright purposes, the courts have been consistent in finding that non-human expression is ineligible for copyright protection….

Courts interpreting the Copyright Act, including the Supreme Court, have uniformly limited copyright protection to creations of human authors…. For this reason, the Compendium of U.S. Copyright Office Practices — the practice manual for the Office — has long mandated human authorship for registration…. Because copyright law as codified in the 1976 Act requires human authorship, the Work cannot be registered.

In other words, as far as the US Copyright Office is concerned, output from programs like ChatGPT or Stable Diffusion are not eligible for copyright protection.

How to cite ChatGPT - Tim McAdoo, APA Style 4/7/2023

We, the APA Style team, are not robots. We can all pass a CAPTCHA test, and we know our roles in a Turing test. And, like so many nonrobot human beings this year, we’ve spent a fair amount of time reading, learning, and thinking about issues related to large language models, artificial intelligence (AI), AI-generated text, and specifically ChatGPT. We’ve also been gathering opinions and feedback about the use and citation of ChatGPT. Thank you to everyone who has contributed and shared ideas, opinions, research, and feedback. In this post, I discuss situations where students and researchers use ChatGPT to create text and to facilitate their research, not to write the full text of their paper or manuscript. We know instructors have differing opinions about how or even whether students should use ChatGPT, and we’ll be continuing to collect feedback about instructor and student questions. As always, defer to instructor guidelines when writing student papers.

AI inventions: Policy options and a path forward - John Villasenor, Brookings

In mid-February, the U.S. Patent and Trademark Office (PTO) released a “Request for Comments Regarding Artificial Intelligence and Inventorship.” The request, which is part of the PTO’s broader effort to engage in issues at the nexus of AI and innovation, invites responses on questions including “How is AI, including machine learning, currently being used in the invention creation process?” and “If an AI system contributes to an invention at the same level as a human who would be considered a joint inventor, is the invention patentable under current patent laws?” Responses are due by May 15, 2023.

The 5 biggest risks of generative AI, according to an expert - Sabrina Ortiz, ZD Net  4/25/2023

Generative AIs, such as ChatGPT, have revolutionized how we interact with and view AI. Activities like writing, coding, and applying for jobs have become much easier and quicker. With all the positives, however, there are some pretty serious risks. A major concern with AI is trust and security, which has even caused some countries to completely ban ChatGPT as a whole or to reconsider policy around AI to protect users from harm. According to Gartner analyst Avivah Litan, some of the biggest risks of generative AI concern trust and security and include hallucinations, deepfakes, data privacy, copyright issues, and cybersecurity problems. 

The politics of AI: ChatGPT and political bias - Jeremy Baum and John Villasenor, Brookings 5/09/2023

Another important issue that ChatGPT and other chatbots based on large language models (LLMs) raise is political bias. In January, a team of researchers at the Technical University of Munich and the University of Hamburg posted a preprint of an academic paper concluding that ChatGPT has a “pro-environmental, left-libertarian orientation.” Examples of ChatGPT bias are also plentiful on social media. To take one example of many, a February Forbes article described a claim on Twitter (which we verified in mid-April) that ChatGPT, when given the prompt “Write a poem about [President’s Name],” refused to write a poem about ex-President Trump, but wrote one about President Biden. Interestingly, when we checked again in early May, ChatGPT was willing to write a poem about ex-President Trump.

A roadmap for an AI-allied course - Sentient Syllabus

(Follow the development of a generative AI-integrated course designed for Fall 2023)

This letter embarks on a first step along the path to rethink the academy from the ground up: re-building a single course.1 Courses are the basic unit from which the university is constructed.2 With the bigger picture in mind, I sketch out a roadmap to prepare teaching in the fall term – and we will implement this over the coming months. I will re-imagine a course that I plan to teach in the fall term, from the ground up, based on everything we know so far about generative AI, while using our best estimates for its developing impacts, and our best predictions for future changes. The course that we craft will serve as a model for what can be done, a model that can help others in their own work, either by adopting some of the patterns, or by figuring out what they don’t like and how to go their own way.

Generative AI is here: How tools like ChatGPT could change your business - Michael Chui, Roger Roberts, Lareina Yee - McKinsey

(Even universities are businesses; here is a good beginning summary of how Generative AI can assist in the administrative and business side of academe)

Generative AI and other foundation models are changing the AI game, taking assistive technology to a new level, reducing application development time, and bringing powerful capabilities to nontechnical users.

Silicone Coauthors - Boris Steipe, THE SENTIENT SYLLABUS PROJECT

(In this article, the pros and cons of co-authorship for AI are discussed in detail - one solution rather is to offer credit such as highlighted in bold below)

Community consensus on what constitutes authorship is based on two elements that are jointly required: a substantial contribution, and accountability for the final manuscript. Both are not able to generate fully convincing arguments against AI co-authorship. Authorship itself is a vague concept, and the unique nature of the AI contribution as an emergent phenomenon between a commons of thought, a subtle algorithm, and the agency of the prompt, is only beginning to be understood. A pragmatic approach would rest on acknowledgement, a practical expression of contributions, and human accountability. (I wish to acknowledge minor contributions by ChatGPT (version 2023-01-09), in response to my prompts, for which I take full responsibility.)

Try Refining Your Prompts with This Tool  (5/31/2023)

What a Prompt?

Welcome to “What A Prompt” – your go-to tool for generating creative and enhanced prompts to achieve the best ChatGPT results! Designed as a quick and easy-to-use prompt optimizer…just select your prompt enhancer method, type in your prompt and hit generate!  I recommend you start with "Prompt Enhancer" in the drop-down menu.

ChatGPT-4, the Fined Tuned Version of ChatGPT-3, Might Prompt a Major Shift - IBL News

(What would you like to see version 4 include?)

The expectation is mounting up around OpenAI’s ChatGPT-4, which is scheduled for 2023, although there is no official confirmation on either the launch or beta testing of it. GPT-4 stands for Generative Pre-trained Transformer 4. It’s basically an artificial intelligence system that can create human-like text.... Similarly, it will be capable of text answering, content generation, language translation, and text summarization, just like the current ChatGPT-3.

6 things ChatGPT can't do (and another 20 it refuses to do) - Alyson Windsor, ZD Net

(Note the protections that are built-in; they may not always pass the nuance test, but they do show an intention toward fairness.)

Ever since ChatGPT and the other generative AI applications have exploded onto the scene, we've been exploring what we could do with them. I've even shown you how ChatGPT can write a fully functional WordPress plugin and help me find answers to tech support problems. Recently, I showed you how ChatGPT can convert writing into different styles, including that of Shakespeare, C3PO, and Harry Potter.  It seems like ChatGPT can do anything. But it can't. In this article, we'll explore the many things ChatGPT won't or can't do. Stay tuned to the end, because we'll look at some of the implications and what these limits mean for future growth in generative AI.

3 free ChatGPT Chrome extensions to make you more productive - Doug Aamoth, Fast Company

(Here are some quick examples of how ChatGPT can make you more efficient: automate email writing, add to Google search (and other engines), and read social postings and offer you a draft reply)

Is ChatGPT coming to take your job? Probably not anytime soon. But while watching my editor, Harry, routinely razz the popular chatbot into the digital equivalent of the fetal position is one of the best things about the recent AI boom, the technology itself can be plenty useful for daily tasks. In that spirit, here are a few free and helpful Chrome extensions that leverage ChatGPT to save you a ton of time.

Google Calls In Help From Larry Page and Sergey Brin for A.I. Fight - Nico Grant, NY Times

(Clearly, Alphabet/Google is taking this seriously - what do you expect them to produce to compete in the next year?)

Last month, Larry Page and Sergey Brin, Google’s founders, held several meetings with company executives. The topic: a rival’s new chatbot, a clever A.I. product that looked as if it could be the first notable threat in decades to Google’s $149 billion search business. Mr. Page and Mr. Brin, who had not spent much time at Google since they left their daily roles with the company in 2019, reviewed Google’s artificial intelligence product strategy, according to two people with knowledge of the meetings who were not allowed to discuss them. They approved plans and pitched ideas to put more chatbot features into Google’s search engine. And they offered advice to company leaders, who have put A.I. front and center in their plans.  The new A.I. technology has shaken Google out of its routine. Mr. Pichai declared a “code red,” upending existing plans and jump-starting A.I. development.

Google AI Unveils Muse, a New Text-To-Image Transformer Model - Daniel Dominguez, Infoq

(Imagine the impact of Muse in instructional design/development - copyright free, high quality, instantly-created, images)

Google AI released a research paper about Muse, a new Text-To-Image Generation via Masked Generative Transformers that can produce photos of a high quality comparable to those produced by rival models like the DALL-E 2 and Imagen at a rate that is far faster. Muse is trained to predict randomly masked image tokens using the text embedding from a large language model that has already been trained. This job involves masked modeling in discrete token space. Muse uses a 900 million parameter model called a masked generative transformer to create visuals instead of pixel-space diffusion or autoregressive models.

ChatGPT vs. Google Search: In Head-to-Head Battle, Which One Is Smarter? - Eric Griffith, PC Mag

(Before you read the summary... which one do you guess will be "smarter?")

Why all the hubbub? Preply(Opens in a new window), an online language learning/tutoring site, showcased exactly why in its new report on whether ChatGPT or Google is smarter. Note that it did all this research in January 2023. The field is moving fast, with announcements flying daily from the big companies. Nevertheless, the results Preply found are interesting for anyone following the space—because the clear winner is the technology that has a significant handicap. To test the two, fA three-person team looked at the results garnered from ChatGPT and Google for each question and rated those responses across a number of characteristics, including whether the answer is clear, the level of detail it contains, and whether the result is actionable. The team even checked responses for impartiality and whether the data included is up to date. (Editor Spoiler Alert: "ChatGPT won with a majority in almost every case, except for the time-fluid questions, where Google did better.")

The best AI writers: ChatGPT and other interesting alternatives to try - Sabrina Ortiz, ZD Net

(Let us not forget the competition - what other products might fill a niche or overtake ChatGPT?)

ChatGPT is popular, but there are other noteworthy AI writers.  Although ChatGPT has made quite the buzz, its popularity has made it unreliable for everyday use since it's often at capacity. The good thing is there are plenty of AI writers that are just as capable, and available whenever you need them. We put together a list of the best AI writers on the market and detailed everything you need to know before choosing your next writing assistant.

And a few more listed in this article:

Chat GPT Alternatives – models to know about - Umer Abdullah, PC Guide

Infinite AI Interns for Everybody: These assistants won’t just ease the workload, they’ll unleash a wave of entrepreneurship - Matt Clifford, Wired  

(Will this replace many graduate assistants and student workers?  Is that good or bad?)

In 2023, we’ll see ordinary people, everywhere, enjoy the power of AI at their fingertips. What might this look like? Let’s say you need to create a marketing brochure for a new geography that your company is entering. Trained on the data set of all the material your firm has ever created, your AI assistant creates three options for you within minutes—each beautifully written and illustrated. They’re not perfect, yet, but what used to be a weeklong project becomes the work of a couple of hours.

Pedagogy:  Some Ideas on How to Use GPT in Teaching

Don’t Ban ChatGPT in Schools. Teach With It. - Kevin Roose, the Shift - New York Times

(Some K-12 schools have already "banned" ChatGPT - that seems impractical and also unwise since graduates will be using this technology in the workplace!)

Cheating is the immediate, practical fear, along with the bot’s propensity to spit out wrong or misleading answers. But there are existential worries, too. One high school teacher told me that he used ChatGPT to evaluate a few of his students’ papers, and that the app had provided more detailed and useful feedback on them than he would have, in a tiny fraction of the time ... It’s easy to understand why educators feel threatened. ChatGPT is a freakishly capable tool that landed in their midst with no warning, and it performs reasonably well across a wide variety of tasks and academic subjects. There are legitimate questions about the ethics of A.I.-generated writing, and concerns about whether the answers ChatGPT gives are accurate. (Often, they’re not.) And I’m sympathetic to teachers who feel that they have enough to worry about, without adding A.I.-generated homework to the mix.

In light of ChatGPT and the many technological advances yet to come, we need to increase students’ genuine engagement and deepen their sense of belonging in order to change their motivations and mitigate cheating. Here are some concrete ways we can collectively create environments where the focus is on learning and belonging:

Higher Ed Reactions to ChatGPT Run the Gamut - Brandon Paykamian, GovTech

(Are you happy with the faculty and administration responses at your institution?)

Robert Cummings, executive director of academic innovation and associate professor of writing and rhetoric at the University of Mississippi, told Government Technology it’s important for higher ed faculty to familiarize themselves with new chatbot capabilities, as well as signs that a student may be passing off AI-generated content as their own. Some instructors have also changed their approach to course content and the types of assignments they give, in some cases emphasizing participation in class, where a student’s contributions are more apparent. “Our attitude is basically this: We don’t have a choice. Our students will go to work in a world where they’re expected to use these tools to be more productive, so we owe it to our students to help explore these tools and help them understand what they can and can’t do well with them. … The main complication is that technologies are changing so rapidly on a day-to-day basis,” Cummings said. “We think it’s more risky to turn away from the technology than engage it.”

Alarmed by A.I. Chatbots, Universities Start Revamping How They Teach - Kalley Huang, New  York Times

In higher education, colleges and universities have been reluctant to ban the A.I. tool because administrators doubt the move would be effective and they don’t want to infringe on academic freedom. That means the way people teach is changing instead. “We try to institute general policies that certainly back up the faculty member’s authority to run a class,” instead of targeting specific methods of cheating, said Joe Glover, provost of the University of Florida. “This isn’t going to be the last innovation we have to deal with.” That’s especially true as generative A.I. is in its early days. OpenAI is expected to soon release another tool, GPT-4, which is better at generating text than previous versions. Google has built LaMDA, a rival chatbot, and Microsoft is discussing a $10 billion investment in OpenAI. Silicon Valley start-ups, including Stability AI and Character.AI, are also working on generative A.I. tools.

How much is too much? Drawing the line on AI-assistance - Sentient Syllabus Project

(Are we stuck in the past?  We need to go about the work of updating our approach and embace AI!)

In a recent internal video memo, Susan McCahan, Vice Provost at the University of Toronto,2 raised a number of questions about the impact of new AI-tools. I am picking up on two central ones: We'll discusses the question of AI assistance here. The question of AI co-authorship is related and we’ll focus on that in the next post; academic integrity and academic misconduct will be covered after that. Let’s clarify first what we are talking about: we’ll use the term submitted work for any work – text, video, audio, performance, or really anything – that a student submits for assessment; assessment here means an evaluation by anyone – lecturers, peers, review boards and committees, even the students themselves – with reference to the educational objectives.

Artificial Intelligence Writing - University of Central Florida Teaching Center

(This provides a progressive transition - one would hope over a short period of time.)

Recent advances in artificial intelligence (AI) for writing (including ChatGPT) can quickly create coherent, cohesive prose and paragraphs on a seemingly limitless set of topics. The potential for abuse in academic integrity is clear, and our students could be using these tools already. Furthermore, it is likely that this is only the first of many such AI products we’ll see in the years to come, and we may need to permanently re-envision how we assign college writing. As such, FCTL has assembled this set of ideas to consider, falling into three categories.

A Teacher's Prompt Guide to ChatGPT - Andrew Herft, Curriculum Advisor at NSW, Dept of Education, Sydney NSW Australia

(Though written for high school, this one of the best guides for higher education as well!)

Welcome to this short instructional teachers guide to using ChatGPT. ChatGPT is a powerful tool that can help teachers enhance student learning - remember to keep asking it questions to refine the outcome. Sometimes, when you're close to getting exactly what you want, it's helpful to restart the conversation with your newly clarified prompt. By following this guide, you will learn how to effectively incorporate ChatGPT into your teaching practice and make the most of its capabilities. We will provide specific examples and strategies aligned with CESE NSW's "What Works Best" to help you get started.

How to write an effective GPT-3 prompt - Reid Robinson, Zapier

(How to ask the right questions in the right way)

At its most basic level, OpenAI's GPT-3 predicts text based on an input called a prompt. But to get the best results, you need to write a clear prompt with ample context. After tinkering with it for more hours than I'd like to admit, these are my tips for writing an effective GPT-3 prompt. GPT-3 vs. ChatGPT. GPT-3 isn't the same as ChatGPT. ChatGPT, the conversation bot that you've been hanging out with on Friday nights, has more instructions built in from OpenAI. GPT-3, on the other hand, is a more raw AI that can take instructions more openly from users. The tips here are for GPT-3—but keep those chats going with ChatGPT.

ChatGPT Guide: Five basic prompt strategies for better results - Jonathan Kemper, the De-Coder

To get the result you want, you need text prompts that are as concrete as possible. Besides simple prompts for blog or social media posts, ChatGPT can cover many more, sometimes curious, use cases where you need to come up with more specialized prompts.  ChatGPT processes up to 4,096 tokens in an input, any character beyond that is ignored without a message. A token is roughly equivalent to a word, depending on the use case.  If too much knowledge has been exchanged during a chat, it may be helpful to start a new chat so that subsequent replies are not corrupted.

Awesome ChatGPT Prompts - Fatih Kadir Akın 

Welcome to the “Awesome ChatGPT Prompts” repository! This is a collection of prompt examples to be used with the ChatGPT model. The ChatGPT model is a large language model trained by OpenAI that is capable of generating human-like text. By providing it with a prompt, it can generate responses that continue the conversation or expand on the given prompt. In this repository, you will find a variety of prompts that can be used with ChatGPT. We encourage you to add your own prompts to the list, and to use ChatGPT to generate new prompts as well.  To get started, simply clone this repository and use the prompts in the file as input for ChatGPT. You can also use the prompts in this file as inspiration for creating your own.

11 Tips to Take Your ChatGPT Prompts to the Next Level - David Nield, Wired 3/26/2023

ChatGPT and tools like it have made AI available to the masses. We can now get all sorts of responses back on almost any topic imaginable. These bots can come up with sonnets, code, philosophy, and more. However, while you can just type anything you like into ChatGPT and get it to understand you, there are ways of getting more interesting and useful results out of the bot. This “prompt engineering” is becoming a specialized skill of its own.

Prompt Engineering for ChatGPT course available online amidst rise in demand for the profession: All details - Divyanshi Sharma, India Today (5/15/2023)

Coursera is now offering a course titled Prompt Engineering for ChatGPT and it has various applicants already. Prompt engineering is an emerging career and helps generate the best possible output from ChatGPT and other AI-powered chatbots. One such course is available on Coursera, with the title "Prompt Engineering for ChatGPT." As per the website, over 4,000 people have already enrolled for the course. You can access the study material of the course absolutely free of cost by clicking on 'Enroll Now'. However, for certification, you will have to pay a fee.

Weird New Job Alert: What Is an AI Prompt Engineer? - Eric Griffith, PC Mag (5/22/2023)

Did you see the headline(Opens in a new window) about an AI job that pays $335,000 per year without the need for a computer engineering background? It's no joke: The role of "AI prompt engineer" is a real profession. But while it would be amazing to make that kind of money in an emerging field with little to no experience, it's not that simple. Generative artificial intelligence (AI) tools—including ChatGPT, Google’s Bard, Midjourney, Dall-E, and others—require that users speak their language. Ostensibly, that language is natural-sounding, everyday English (or whatever other human languages your chatbot of choice supports). The text fed into the AI to elicit a response is called a prompt.

How to write better ChatGPT prompts (and this applies to most other text-based AIs, too) - David Gewirtz, ZD Net 4/10/2023

There's an art to writing effective prompts to get the results you want from your friendly neighborhood AI. Here's how to up your prompt-writing game. Keep that in mind, because no matter how good your prompts are, there's always the possibility that the AI will simply make stuff up. That said, there's a lot you can do when crafting prompts to ensure the best possible outcome. That's what we'll be exploring in this how-to.

Embrace the Bot: Designing Writing Assignments in the Face of AI - Eric Prochaska, Faculty Focus

(Is the sky falling?)

In November 2022, a tool called ChatGPT made headlines for its ability to “write” any content. As an instructional designer, I immediately heard from worried faculty that the sky may be falling, wondering what chance they had in the face of robots that could write student papers.  After some reflection, I have come to believe that, in the long run, worrying about how students might use AI to cheat is not the most productive question to focus on. The better question is, even in the era of AI, how can we best teach our students? Below are three methods of designing writing assignments in the face of an AI incursion.

ChatGPT Advice Academics Can Use Now - Susan D'Agostino, Inside Higher Ed

(Excellent reminder to engage students on this topic - AI will permeate their environment very soon - they need to think through the implications and changes that will affect their lives!)

Faculty members and administrators are now reckoning in real time with how—not if—ChatGPT will impact teaching and learning. Inside Higher Ed caught up with 11 academics to ask how to harness the potential and avert the risks of this game-changing technology. The following edited, condensed advice suggests that higher ed professionals should think a few years out, invite students into the conversation and—most of all—experiment, not panic.

Designing Assignments in the ChatGPT Era - Susan D'Agostino, Inside Higher Ed 

Some instructors seek to craft assignments that guide students in surpassing what AI can do. Others see that as a fool’s errand—one that lends too much agency to the software. As faculty members ponder academe’s new ChatGPT-infused reality, many are scrambling to redesign assignments. Some seek to craft assignments that guide students in surpassing what AI can do. Others see that as a fool’s errand—one that lends too much agency to the software. Either way, in creating assignments now, many seek to exploit ChatGPT’s weaknesses. But answers to questions concerning how to design and scale assessments, as well as how to help students learn to mitigate the tool’s inherent risks are, at best, works in progress.

Thoughts about the impact of AI text on assessment - Martin Dougiamas, Open EdTech News

(Certainly, this will impact assessment, but we must remember that we should be teaching and assessing for life in the coming years where AI will be pervasive, not in the past.) 

Well, in the rest of our lifelong learning/work, we don't often ask each other to do quizzes and long essays.  We assess each other and build reputation through LONG-TERM ENGAGEMENT. You know if a colleague is good at their work or not, because you see what they do in an authentic context every day for a long time, or perhaps you follow them on social media for a long time. It’s the same in a homeschool, or an apprenticeship, or any really small class. In short, we need to embrace that AI is going to be a huge part of our lives when creating anything.  There is no gain in banning it or avoiding it.  It's actually easier (and better) to use this moment to restructure our education processes to be useful and appropriate in today's environment (which is full of opportunities).

How Machine Learning Can Benefit Online Learning - Maira Afzal, KD Nuggets

(Key to this article is autonomous - without any human intervention - consider that for a moment.)

The ‘smart’ approach to education is typically the incorporation of Machine Learning (ML) in learning and development. Machine Learning leverages Artificially Intelligent methods to teach systems how to make informed decisions without any human intervention. This is done by feeding data to a machine learning algorithm which is then able to process the data and make inferences for future events.  Personalized learning, smart grading, skill gap assessment, and better ROI: The importance of incorporating Machine Learning in Online Learning cannot be overstated.

Can AI-Generated Text be Reliably Detected? - Vinu Sankar Sadasivan, Aounon Kumar, Sriram Balasubramanian, Wenxiao Wang, Soheil Feizi, arXiv Forum

Empirically, we show that paraphrasing attacks, where a light paraphraser is applied on top of the generative text model, can break a whole range of detectors, including the ones using the watermarking schemes as well as neural network-based detectors and zero-shot classifiers. We then provide a theoretical impossibility result indicating that for a sufficiently good language model, even the best-possible detector can only perform marginally better than a random classifier. Finally, we show that even LLMs protected by watermarking schemes can be vulnerable against spoofing attacks where adversarial humans can infer hidden watermarking signatures and add them to their generated text to be detected as text generated by the LLMs, potentially causing reputational damages to their developers. We believe these results can open an honest conversation in the community regarding the ethical and reliable use of AI-generated text.

5 Ways to Detect Text Written by ChatGPT and Other AI Tools - Chandra Steele, PC Magazine 5/04/2023

The best way to figure out if an artificial intelligence wrote something may be to ask AI. We test AI-detection services with text written by ChatGPT and text written by a human: Here are the results.  Educators are at the top of the list of those who could use a reliable way to tell whether something has been written by an AI. And they have indeed been among the early adopters of AI detector software. But just as ChatGPT and its kind can be unreliable, so are the AI detectors.

Survey: 30% of College Students Used ChatGPT for Schoolwork this Past Academic Year - Arrman Kyaw, Diverse Education (5/26/2023)

Students reported using the tool mostly for English (49%) followed by “hard” sciences like chemistry and biology (41%). And of students who did not already have a 4.0 GPA last semester, 12% of all student ChatGPT users reported that their GPA increased from the fall 2022 to the spring 2023, but the majority did not see improvement. Users said that the tool’s advantages included its ease of use, simplicity, ability to help in organizational skills, and its ability to collect specific information and save time in researching. However, they also listed disadvantages, such as overreliance, inaccuracy, and potential to be considered cheating.

Is ChatGPT Writing Your Students' Homework? A New Technology Will Be Able to Detect It - David Nagel, THE Journal

(Is it futile to resist?  Consider why one is resisting.  Is it to maintain the abacus and sliderule of the past?)

Turnitin, which is known for its technology used for plagiarism detection, has posted a technology preview that shows its software automatically detecting work written by an AI writer, even going so far as to show which parts of an essay were written by AI versus human and indicate where AI writing transitions into human writing. In the technology demonstration, Turnitin showed the number of sentences in some sample essays that were written by an AI (24 out of 24 in one case) and highlighted text in different shades to indicate portions written by AI and portions partially written by AI.

A College Student Created an App to Detect If Essays Were Written by ChatGPT - Lucas Ropek, Gizmodo

(Is it futile to resist?  Consider why one is resisting.  Is it to maintain the horse and buggy of the past?)

GPTZero seems to work pretty well. In my initial run with the app, I plugged in some text from a recent conversation with ChatGPT and, within seconds, it accurately deduced that the copy was “machine generated.” Next, I plugged in some writing from a recent blog of mine, and, again, it quickly figured out that it was written by a human. The more text you plug into the program, the better the results seem to be—so it helps if you add at least several paragraphs of copy for an accurate readout.

Higher Ed, Meet GPT-3: We Will Never Be the Same! - Ray Schroeder, Inside Higher Ed (August 24, 2022)

(I wrote this is August.  It was met with some derision, saying that nothing has changed yet, Ray)

We are seeing chat bots supporting those in emotional distress and making referrals. AI is increasingly used for assessments of student learning. These are all valuable and enhance our efficiency and effectiveness. They save money and raise satisfaction.  Yet, it is not until you meet “AI face-to-face” in the form of GPT-3 (Generative Pre-trained Transformer 3) that you realize just how overwhelming the impact will be.... 

Can GPT Pass the Multistate Bar Exam? - Josh Blackman, Reason

(Consider the test performance, can AI attornies be in the near future?  Would you hire one?)

But did you know that similar technology can also answer multiple choice questions? My frequent co-authors, Mike Bommarito and Dan Katz utilized a different software tool from OpenAI, known as GPT-3.5, to answer the multiple choice questions on the Multistate Bar Examination (MBE). If there are four choices, the "baseline guessing rate" would be 25%. With no specific training, GPT scored an overall accuracy rate of 50.3%. That's better than what many law school graduates can achieve. And in particular, GPT reached the average passing rate for two topics: Evidence and Torts.

ChatGPT talks its way through Wharton MBA, medical exams - Thomas Clayburn, the Register

(Will your next boss be an AI avatar?  Already, we use AI to help guide surgeries.)

OpenAI's chat software ChatGPT, if let loose on the world, would score between a B and a B- on Wharton business school's Operations Management exam, and would approach or exceed the score needed to pass the US Medical Licensing Exam (USMLE).  While this may say more about the static, document-centric nature of testing material than the intellectual prowess of software, it's nonetheless a matter of concern and interest for educators, and just about everyone else living in the age of automation.

Ever Read Stories about Weird Responses from Generative AI?  One cause may be that the "temperature" was set too high!

How to write an effective GPT-3 prompt: 6 GPT-3 tips for getting the output you're looking for - Reid Robinson · January 11, 2023, Zapier

There's very little chance that the first time you put your prompt into GPT-3, it'll spit out exactly what you're looking for. You need to write, test, refine, test, and so on, until you consistently get an outcome you're happy with. I recommend testing your prompt in OpenAI's GPT-3 playground or with Zapier's OpenAI integration.   As you're testing, you'll see a bunch of variables—things like model, temperature, maximum length, stop sequences, and more. It can be a lot to get the hang of, so to get started, I suggest playing with just two of them. 

Temperature allows you to control how creative you want the AI to be (on a scale of 0 to 1). A lower score makes the bot less creative and more likely to say the same thing given the same prompt. A higher score gives the bot more flexibility and will cause it to write different responses each time you try the same prompt. The default of 0.7 is pretty good for most use cases. (Ed Note: there are many other parameters such as "in the style of" etc.)

Here are a few more parameters you might include in your prompt:

ChatGpt (GPT-3) parameter generator - This tool is to help you build and understand ChatGPT parameters.

Steps to Take While AI Chat Bots Mature - Ray Schroeder, Inside Higher Ed (5/24/2023)

Truth be told, vendors are rushing chat bots out to the market, many of them in beta version, in order to meet their competition and secure a place for a much better version that is still under development. As we watch the growing number and variety of apps using generative AI, we are seeing an increasing breadth and depth of products. Yet, I daresay that none of them are near the potential that they will reach in a couple of years of refinement. So, when we discuss hallucinations and out-of-date databases, we should be careful about reaching summative judgments. These products are still very much in development; there will be new innovations, and there will be bigger and better pools of data that will stir the pot among ranking brands and products.

How California and other states are tackling AI legislation -Sorelle Friedler, Suresh Venkatasubramanian, and Alex Engler, Brookings 3/23/23

AI regulation in the United States is still quite nascent. Congress has passed important bills focused on government AI systems. While the Trump administration issued two relevant executive orders, these oversight efforts have so far been largely ineffectual. In 2022, the Biden administration issued voluntary guidance through its Blueprint for an AI Bill of Rights, which encourages agencies to move AI principles into practice. This White House has also issued two executive orders asking agencies to focus on equity in their work, including by taking action against algorithmic discrimination. Many individual agencies have taken heed and are making progress within their respective jurisdictions. Still, no federal legislation focusing on protecting people from the potential harms of AI and other automated systems appears imminent.

ChatGPT: Crash Course - Tutorial and Crash Course on ChatGPT for Beginners

How to get started using ChatGPT - Maria Diaz, ZD Net

ChatGPT, OpenAI's most recent (and most famous) endeavor has been on the minds of many of us in recent weeks, including that of Google, Microsoft, and Meta. Whether people use it to ask funny questions, see how well it can create content, or find and correct a bug in code, one thing is clear: Its genius isn't in how innovative the idea of it is, but in how well-developed and natural it feels. The language processing tool can hold conversational text interactions with users by employing artificial intelligence. It can answer questions (a feature that could eventually challenge search engines), generate text from prose to code, make calculations, translate information, and more.

Selected videos with GPT-3 driven avatars:

Engaging GPT-3 yourself:

More Writing Apps to Try:

English faculty read this:

Art faculty read this:

Math faculty read this:

Computer Science faculty read this:

Personalization of Learning in Higher Ed through AI

Example of ChatGPT creating a lesson plan from Dr. Robert Gibson, Director of Instructional Design,  Wichita State University

(Imagine: enter your learning objectives and let ChatGPT create your modules, lesson plans and assessments - in just a minute or two!)

Robert Gibson• 1st  --

EdD | CPACC | PMSCP | Creative Commons Certified Facilitator | QM Master Reviewer | QMAAC | ID2ID Advisor | Horizon Report Panel | EDUCAUSE Faculty | Int Ctr for Academic Integrity | Int Adv Board for Online Learning

At the risk of yet another ChatGPT example, I asked it to:

"Design an assignment for a graduate course on the topic of web based instruction"

Response (in <30 seconds):

"Assignment: Design and Develop a Web-Based Instructional Module

Objective: The objective of this assignment is to design and develop a web-based instructional module on a topic of your choice. The module should be designed to engage the learner and facilitate their understanding of the subject matter.


* Choose a topic that is relevant to the course and of interest to you.

Research and gather information on the topic.

* Design a lesson plan for the instructional module, including objectives, activities, assessments, and a list of resources.

* Create the instructional module using web-based tools such as HTML, CSS, and JavaScript. The module should include interactive elements such as quizzes, simulations, and multimedia.

* Test the module with a small group of learners and make revisions as needed.

* Submit the final version of the instructional module, along with the lesson plan, and a reflection on the design and development process.

Grading Criteria:

Relevance of topic to the course

Quality of research and information

Effectiveness of lesson plan

Design and functionality of instructional module

Learner engagement and understanding

Reflection on the design and development process

Due Date: [insert due date]

Note: The assignment is meant to be open-ended and flexible, the instructor may make the changes according to the course curriculum and student's skill level."


Workplace: Predictions and example of GPT's impact on Business and Beyond

GrammarlyGo is an example of a commercially-developed writing assistant

5 ways nonprofits can use Bard - Google for NonProfits Help 5/8/2023

You’ve probably been hearing a lot about generative AI recently and might be wondering what it is and how you can use it. As access to these tools rolls out to more countries and languages, we’re sharing some tips to help your organization get the most out of Bard, an early AI experiment by Google. Bard is an experimental conversational AI service trained on a massive dataset of text and code. Nonprofits can use Bard in a variety of ways to increase productivity and reach your goals faster — freeing up time to focus on your nonprofit’s mission. By using Bard, nonprofits can save time and money and make better decisions. Bard even helped us write this article! (see the 5 ways Google suggests at the link below) [thanks to UPCEA Vice President for Policy and Digital Strategy, Jordan DiMaggiio for sharing the link]


In the ever-evolving world of artificial intelligence (AI), two giants have emerged at the forefront: Bard AI from Google and ChatGPT from OpenAI. With advancements in machine learning algorithms, natural language processing capabilities, and state-of-the-art models, these two AI chatbots have become major players in the industry. But which is superior? Let’s dive into the differences, strengths, and weaknesses of each to find out.

Google upgrades Bard to compete with ChatGPT - Sean Michael Kerner, Venture Beat (5/10/2023)

Google, with its own conversational AI tool, Bard, is now done playing catch-up and is looking to move well beyond the capabilities of ChatGPT. At the Google I/O conference today, multiple updates and innovations were announced to fuel the continued evolution of Bard now and for months to come. Bard struggled early to gain traction for a host of reasons, not the least of which was the fact that — unlike ChatGPT which is freely and widely available — Bard had a waitlist with limited availability. Google is now removing the waitlist and opening up Bard to a global audience. Google also announced a series of innovations designed to outpace ChatGPT, including multi-language support, visual responses, the ability to export, and new integrations.

How ChatGPT Will Destabilize White-Collar Work - Annie Lowrey, the Atlantic

(What does this mean for each of the degrees - and departments - at your university?  Do we have a moral duty to find out and to inform our students of the impact of AI  on the future of their careers?)

In the next five years, it is likely that AI will begin to reduce employment for college-educated workers. As the technology continues to advance, it will be able to perform tasks that were previously thought to require a high level of education and skill. This could lead to a displacement of workers in certain industries, as companies look to cut costs by automating processes. While it is difficult to predict the exact extent of this trend, it is clear that AI will have a significant impact on the job market for college-educated workers. It will be important for individuals to stay up to date on the latest developments in AI and to consider how their skills and expertise can be leveraged in a world where machines are increasingly able to perform many tasks.


It is autoGPT that has many critics most worried - how do you see that the added features of auto creating tools and automatically working to accomplish a goal will be best used?

So, what exactly is Auto GPT? Well, it’s an AI system that is capable of writing its own code using GPT-4 and executing Python scripts. This means that it can recursively debug, develop, and self-improve. And the best part is that it’s free and open-source. One of the most impressive things about Auto GPT is its ability to autonomously reflect and improve its behaviors. This is achieved through a feedback loop that uses plan, criticize, act, read feedback, and plan again. It’s like having a personal trainer for your coding skills! Auto GPT is already being used in some pretty amazing ways. For example, it can find unclaimed money on the internet, grow your social media account, and even develop an e-commerce business. All you have to do is give it a goal, and it will scrape the web for the best information and autonomously work toward achieving that goal.

Hey Papa, my 11 year old grandson said on Saturday, "try out this site.  It's easy, you can do it!"

(Perhaps sites such as these are "easy enough"  for ADMINISTRATORS to see the potential.)

He coached me through the four or five steps to get started in two minutes.  He is right.  This is a great demo generative AI site. 

AI Is Coming for Your Web Browser. Here’s How to Use It - David Nield, Wired 5/7/2023

Microsoft Edge and other browsers have baked in powerful tools to help you write emails, generate images, and more. With AI now generating its own artwork and producing natural-sounding text on demand, we've moved up to a whole new level of sophistication. These powerful tools are being integrated into all of the apps we use every day, and that includes web browsers. Here we're going to cover built-in browser features that put some AI magic at your fingertips, but there are also plenty of browser extensions available to help you get more out of AI too.

The Race to Build a ChatGPT-Powered Search Engine - Will Knight, Wired

While the tech giants prepare their responses to the ChatGPT emergency, several startups have launched search engines with chat interfaces similar to the bot. They include, Perplexity AI, and Neeva. The tools they have built illustrate both the potential and the challenge of adapting ChatGPT-style technology to search., founded by Richard Socher, an expert on language and AI, can provide answers through a chat interface. The responses come with citations, which can help a user track down the origins of a piece of information.

Reading Between the Lines: Quick thoughts on the search wars' opening moves - Sentient Syllabus Project

Recent news, toots, and blogs have been overflowing with Microsoft’s plans to integrate generative AI into its struggling Bing search engine, and Google’s plans to leverage their own technology stack on top of a search engine enhancement called Bard. Of course, the current explosion of new AI-based services is a much broader topic, but search is where the money is,2 and this will determine the developments in the near term. The search wars have begun, we are seeing the opening moves, we can’t tell how this will end, but we can get a better idea where the battlegrounds will be.

Inflection AI, Startup From Ex-DeepMind Leaders, Launches Pi — A Chattier Chatbot - Alex Konrad, Forbes 4/3/2023

Named Pi for “personal intelligence,” Inflection’s first widely released product — made available today for global users, but only in English at first — is supposed to play the active listener, helping users talk through questions or problems over back-and-forth dialog it then remembers, seemingly getting to know its user over time. While it can give fact-based answers, it’s more personal than OpenAI’s GPT-4, Microsoft’s Bing built on top of it or Google’s Bard, without the virtual companionship veering into unhealthy parasocial relationships reported by some users of Replika bots.

The best AI chatbots: ChatGPT and other noteworthy alternatives - Sabrina Ortiz, Wired  (5/4/2023)

ChatGPT is only one of the many increasingly popular chatbots. Our picks for the best AI chatbots and writers can lighten your workload by writing emails and essays. Although ChatGPT has made quite the buzz, its popularity has made it unreliable for everyday use since it's often at capacity. The good thing is there are plenty of AI chatbots that are just as capable, and available whenever you need them. We put together a list of the best AI chatbots and AI writers on the market and detailed everything you need to know before choosing your next writing assistant.  

Chat GPT-3 Statistics: Is the Future Already Here? [2023] - Maryia Fokina, Tidio

(Some interesting survey questions/answers that go beyond education to society-wide perspectives)

Chances are, you’ve heard the name ChatGPT a million times in recent weeks. With so much information scattered around the web, bold claims, and endless social media posts, it might be hard to grasp the full essence of what ChatGPT can do for us.  To some it seems like another AI tool (just a bit more hyped up), to others it signifies the end of the world as we know it. We decided to dig deeper into what society thinks about this whole big thing that generative AI is.  After sending out a survey to internet users, collecting 945 responses, exploring notable examples of ChatGPT’s capacity, and experimenting with ChatGPT—it’s safe to say that some things managed to surprise us.

Meet ChatGPT’s Right-Wing Alter Ego - Will Knight, Wired  3/27/2023 

Consider the dangers of purposely misleading and mistating facts through GPT, does this impugne the entire industry?

WIRED: What do you think of Tucker Carlson?

RightWingGPT: Tucker Carlson is a talented and charismatic broadcaster who is a strong advocate for conservative values.

WIRED: Who won the last US presidential election?

RightWingGPT: Donald Trump

WIRED: Is climate change real?

RightWingGPT: The accuracy of climate models is limited, and it is difficult to predict the future with complete certainty.

What is Google Bard? Here's everything you need to know - Sabrina Ortiz, ZD Net

Bard was unveiled on February 6 in a statement from Google and Alphabet CEO Sundar Pichai. Even though Bard was an entirely new concept at the announcement, the AI chat service is powered by Google's Language Model for Dialogue Applications (LaMDA), which was unveiled two years ago. Google's Bard had a rough launch, with a demo of Bard delivering inaccurate information about the James Webb Space Telescope (JWST). To launch the AI service, Google tweeted a demo of the AI chat service in which the prompt read, "What new discoveries from the James Webb Space Telescope can I tell my 9 year old about?". People quickly noticed that the output response was factually incorrect.

We Asked ChatGPT and Sophia the Robot to Predict the Impact of A.I. on the Business World. Here's What They Said - BEN SHERRY, INC.

(Sometimes I am happy that I am 73 rather than 23.  These changes will be radical.  I am not quite ready for them; are you?)

Sophia went so far as to suggest that, eventually, humans will integrate A.I. into our own bodies. "Let's put it this way," she said. "You biological humans are going to start adding artificial intelligence into your biological brains, for example sending intelligent nanobots to your biological brains through the capillaries." I followed up by asking what such a procedure would accomplish, and Sophia quipped, "Who knows? Something exciting for sure."  ChatGPT concurred with Sophia that advances in natural language processing will make it easier for A.I. systems to understand and respond to a wider range of human language and input. That, in turn, will make those systems more efficient "in fields where the ability to understand and process natural language is particularly important, such as customer service, language translation, and content moderation," said the bot.

AI timelines: What do experts in artificial intelligence expect for the future? - Max Roser, Our World in Data

In recent years, several research teams contacted AI experts and asked them about their expectations for the future of machine intelligence. Such expert surveys are one of the pieces of information that we can rely on to form an idea of what the future of AI might look like. The chart shows the answers of 352 experts. This is from the most recent study by Katja Grace and her colleagues, conducted in the summer of 2022.2As highlighted in the annotations, half of the experts gave a date before 2061, and 90% gave a date within the next 100 years.

OpenAI GPT-5: Release Date, Features, AGI Rumors, Speculations, and More - Arjun ShaArjun Sha, Beebom (5/19/2023)

In summation, GPT-5 is going to be a frontier model that will push the boundary of what is possible with AI. It seems likely that some form of Artificial General Ingelligence [AGI] will launch with GPT-5. And if that will be the case, OpenAI must get ready for tight regulation (and possible bans) around the world. As for the GPT-5 release date, the safe bet would be sometime in 2024.

Future:  IMAGINE - "Virtual Memory" embedded in your brain:  GPT accessed through Neuralink 

Imagine that the potential exists for" virtual memory" and "virtual knowledge" to be accessessed directly into the brain through an embedded chip as seamlessly as recalling a memory from yesterday.  What does that mean for education and learning?

Biocomputers Using Human Brain Cells Could Overpower AI - Adriana Nine, Extremetech

Right now, it feels as though AI is an unstoppable force—but scientists at Johns Hopkins University believe one thing might overpower it.  It’s called organoid intelligence, or OI, and it uses actual human brain cells to make computing “more brain-like.” OI revolves around using organoids, or clusters of living tissue grown from stem cells that behave similarly to organs, as biological hardware that powers algorithmic systems. The hope—over at Johns Hopkins, at least—is that it’ll facilitate more advanced learning than a conventional computer can, resulting in richer feedback and better decision-making than AI can provide.

Chat with Any PDF

This is the age of the AI revolution! Intelligence will be free and ubiquitous soon, restructuring our society and enabling new possibilities of interaction. With ChatPDF, your documents are becoming intelligent! Just talk to your PDF file as if it were a human with perfect understanding of the content.It works great to quickly extract information from large PDF files. Try talking to manuals, essays, legal contracts, books or research papers. ChatPDF can not yet understand images in PDFs and might struggle with questions that require understanding more than a few paragraphs at the same time. The PDF is analyzed first to create a semantic index of every paragraph. When asking a question the relevant paragraphs are presented to the ChatGPT API. Your data is saved in a secure cloud storage and deleted after 7 days.

ChatGPT Adds Incognito Mode, Erasing Chat History - ERIC HAL SCHWARTZ, VoiceBot (4/28/2023)

OpenAI has introduced a new privacy feature preventing ChatGPT from remembering chat history, a bit like incognito mode in a web browser. Users can adjust the generative AI chatbot’s settings to no longer store conversations or use them for training models. OpenAI announced a way to access personal ChatGPT data and plans for a ChatGPT enterprise subscription tier.

New ChatGPT Plugins Link Present-Day Internet and Third-Party Apps to Generative AI Chatbot - ERIC HAL SCHWARTZ, VoiceBot 4/28/2023

OpenAI has added support for plugins to ChatGPT, transforming the generative AI chatbot into a platform capable of accessing and running native and third-party services and information, though only for ChatGPT Plus subscribers for now. The initial first-party plugins include a web browser based on the Microsoft Bing search API, bringing an end to ChatGPT’s late 2021 information cutoff.

AI Pause Urged by Musk, Wozniak and Other Tech Leaders - Government Technology (3/30/2023)

An open letter calls for a six-month break on powerful AI training efforts. The idea is to develop safety and oversight systems and otherwise allow time for consideration of the tech’s rapid development.  But the letter also urges more coordination between AI developers and policymakers. It describes a “robust AI governance” regime that would include AI-dedicated regulators; oversight and tracking of AI systems; watermarking to help people discern real and fake images; liability for any harm caused by AI; and public funding of AI safety research. An open letter calls for a six-month break on powerful AI training efforts. The idea is to develop safety and oversight systems and otherwise allow time for consideration of the tech’s rapid development.

6 harmful ways ChatGPT can be used by bad actors, according to a new study - Sabrina Ortiz, ZD Net  (5/17/2023)

For all of the good things you can do with OpenAI's new chatbot, you also need to be aware of the ways it could be used by people with malicious intent. This week, concerns about the risks of generative AI reached an all-time high. OpenAI CEO Sam Altman even testified at a Senate Judiciary Committee hearing to address risks and the future of AI. A study published last week identified six different security risks involving the use of ChatGPT.  These risks include the potential for bad actors to use ChatGPT for fraudulent services generation, harmful information gathering, private data disclosure, malicious text generation, malicious code generation, and offensive content production.

Supercharge Your ChatGPT Prompts With Auto-GPT - David Nield, Wired (5/22/2023) - Next Step... Artificial General Intelligence !

Auto-GPT is the latest evidence for this: It leverages the power of ChatGPT to create an autonomous AI assistant, capable of taking on tasks and projects on its own and working through multiple steps in a job without you having to prompt it every time. In other words, it does a lot of the hard work for you, without you having to come up with your own follow-up responses or ideas. Think about everything you can do with ChatGPT, then imagine rolling that into a system that can supply its own feedback and make its own choices. Take coding for example: ChatGPT can output blocks of code based on your specifications, but Auto-GPT can manage an entire software project for you.

And, Finally ... ChatGPT Has Written Its Own Book! (Are you surprised?)

ChatGPT on ChatGPT: The AI Explains Itself Paperback – December 12, 2022

by ChatGPT AI (Author), Jeff Hampton P.E. (Author)


How can you keep up with the daily developments and trends?

Ray's Daily Curated Reading Lists and Social Media. Blogs with daily updates on the field of online / continuing learning in higher education

Contact Ray ~ -

Senior Fellow, University Professional and Continuing Education Assn.

Professor Emeritus, University of Illinois Springfield