If you use or you’re even thinking about using ChatGPT to help you write any kind of technical article, technical video, presentation, course, podcast, even an email, let me show you why you have to be cautious about using ChatGPT in the process, because it can be completely wrong, confidently wrong. It can give you answers that look true, but aren’t, and this could have serious implications if you’re using ChatGPT as a technical source of truth. ♫(Music)♫ First off, let me say, I think ChatGPT is amazing, I love it! When I got the chance to buy the subscription for ChatGPT+, that was one of the quickest and easiest purchases I’ve made in years, but I’ve seen an incredible amount of misplaced trust in the results from ChatGPT, and it’s from a misunderstanding about generative AI and how it works. Example: A few days ago I gave ChatGPT a single, specific, verifiable technical question: What was the first book on SQL? And ChatGPT answered, “The first book on SQL was A Guide to the IBM Relational Database Interface by Don Chamberlin and Robert Boyce, published in 1974. This book was written to doc---” Okay, this is a well-written, convincing, believable answer. If you know your SQL history, you know this is the right timeframe, it’s mentioning the right companies, even the right names. There’s just one problem. There is no such book. This doesn’t exist, and it’s not a manual or a conference paper either. You can search the web, you can search Don Chamberlin’s bibliography, you won’t find it because ChatGPT made this up. It is a generative AI. You give it a prompt and it will generate realistic sounding results for you based on consuming and analyzing massive amounts of data, but getting a realistic and convincing answer is not the same thing as getting an accurate answer. And some of the results you get from ChatGPT, well, they’re often correct, mostly correct, but they can also be completely wrong. And it doesn’t stop there, because ChatGPT then happily led me down a complete rabbit hole of BS, even generating fake citations. When it gave me that answer about that first SQL book, I then asked: Do you have a source for that answer? And ChatGPT said, “Yes, my source for the first book on SQL being A Guide to the IBM Relational Database Interface is ‘The Birth of SQL’ article by Donald Chamberlin in the IEEE Annals of the History of Computing Journal, Volume 32, no. 3, pages 4-15, Jul-Sept 2010.” Another well-written, authoritative sounding, convincing answer. And also, complete rubbish. I can look up the IEEE Annals of the History of Computer, Volume 32, no. 3, July-Sept 2010, and that page, 4-15, there is an article by Hans Rudiger Wiehle. There is nothing here by Donald Chamberlin, there is no “Birth of SQL” article here. He never wrote it. I then asked: Who is the publisher of that book, a book I know doesn’t exist, and I got, “The publisher of A Guide to the IBM Relational Database Interface was the IBM Research Lab in San Jose, California. The book was published in 1974 as a technical report (IBM Research Report RJ909).” Again, sounds great. And again, none of this is true. IBM Research Report RJ909 does exist, but it’s an article by E. F. Codd about normalization, and it was published three years before that in 1971. And you can even tell ChatGPT it’s wrong, and it will admit it, and it will still lead you down the wrong path. I told it: A Guide to the IBM Relational Database Interface does not exist, and ChatGPT said, “I apologize for the confusion in my previous response. Upon further investigation, it appears that A Guide to the IBM Relational Database Interface may not be a correct or complete title for the book. After reviewing various sources, it seems that the book was originally titled SEQUEL: A Structured English Query Language, and was published by IBM in 1974 as a technical report (IBM Research Report RJ3418).” Nope! Well, this title actually is a real publication, but it wasn’t an IBM Research Report, it was a conference paper for the ACM, and only 20-something pages, definitely not a book. And ChatGPT continued, “The book was later reprinted in 1976 by Addison-Wesley as Structured Query Language (SQL): A Practical Introduction.” Yet again, not true. There is a book with this exact title, but it wasn’t published until nearly 20 years later, it wasn’t published by Addison-Wesley, and it was written by a completely different author. Okay, to understand why this happens, think about other generative AIs we have for images, like DALL-E, Midjourney, and Stable Diffusion. You can give them a prompt like: I want a photograph of a brown, soft toy rabbit holding a telescope. And they can generate brand-new images for you. Now sometimes what you get back might be exactly what you wanted, and sometimes it’s just wrong. The results can be weird, even creepy, because these AIs have been trained on staggeringly huge numbers of existing images, images which include ideas like what does a photograph look like, what does a soft toy look like, what’s a rabbit, what’s a telescope? And it’s then combining different qualities of those images in new ways to create brand-new images. But the AI doesn’t actually understand what a rabbit is or what a telescope is. It doesn’t understand biology. It doesn’t understand you look through a telescope with your eyes, not your nose. It doesn’t understand why this is wrong or why this is a complete monstrosity. It’s doing its best to generate a new image based on the qualities of the words that I’ve used, the prompt that I’ve given it. And the thing is, when what you get from a generative AI is an image, it’s often quite easy for you to instantly recognize, well, that’s not right. But when you’re getting text, it’s much more difficult. It can be deceptive. I mean, after all, ChatGPT is designed to generate these well-written, convincing, believable answers, answers which read like the kind of trusted, authoritative text we’ve read for years, and at first glance, this answer looks correct, it looks true. But it isn’t. But, what if I just copied and pasted this into some article I was writing, or a book or a video course, and then someone tried to find that book or follow that string of citations and then call me on it? That is not a good look for me to just say, well, that’s what ChatGPT told me. Now, are things going to get better? Absolutely. Generative AI is getting better all the time. And if I asked ChatGPT that same question today, I’d get a different answer. Whether it’s right or not, that’s a different question. But still, we are not at the point where you can use any of these as a technical source of truth. You need to fact check everything you get from ChatGPT because it can sound extremely convincing, even when it's completely wrong.
Research AI tools are really helpful with managing research materials and discovering new sources of information.
ChatGPT For Dummies demystifies the artificial intelligence tool that can answer questions, write essays, and generate just about any kind of text it's asked for.
After having read this book, you will be confident to participate in public discussions about how this new generation of language models will impact society. You will be aware of the risks and pitfalls these technologies can bring along, and how to deal responsibly when making use of tools built from AI technology in general.
With in-depth coverage of GPT 2, GPT 3, and GPT 4, this book provides a comprehensive overview of the most cutting-edge technology in the world of AI-based text generation.
This book will show how generative technology works and the drivers. It will also look at the applications – showing what various startupsand large companies are doing in the space. There will also be a look at the challenges and risk factors.
Have we finally discovered the holy grail of AI - machines that match or exceed human intelligence? Which industries and professions will thrive, and which will wither? What risks and dangers will it pose? How can we ensure that these systems respect our ethical principles? Will the benefits be broadly distributed or accrue to a lucky few? How will GAI alter our political systems and international conflicts? Are we merely a stepping stone to a new form of non-biological life, or are we just getting better at building useful gadgets? Generative Artificial Intelligence: What Everyone Needs to Know? equips readers with the knowledge to answer these pressing questions.
"Chan and Collotons book is one of the first to provide a comprehensive examination of the use and impact of ChatGPT and Generative AI (GenAI) in higher education.
With Artificial Intelligence creating huge opportunities for learning and employee development, how can learning professionals best implement the use of AI into their environment?
