The other odd aspect of AI is that it tends to spawn other fields in computer science, some of these, like Computer Vision are obvious, but others like Human-Computer Interaction are an outcome of the question of how can we ask a computer to do things. Now we see the field of Machine Learning standing more-or-less on its own away from the rest of AI. A field tends to be AI right up until it becomes popular, and then it\u2019s just computing.<\/p>\n\n\n\n
I started working in AI during a winter, roughly in 2004 and staring a master\u2019s degree in 2007. My introduction to AI came from the perspective of Knowledge Based Systems. We focused on how to organize information in such a way that we could find solutions to hard problems (in the computer science sense) without necessarily having to find the optimal solution. We used mechanics like And-Trees and Or-Trees (and their families) and Genetic Algorithms and when we talked about machine learning we focused on systems that tended to build knowledge representations like case-based reasoning or knowledge trees. Our work focused on building systems that experts in fields could describe and use.I liked working on these projects because there was as much interesting information coming from the field as the AI techniques.<\/p>\n\n\n\n
We tended to skip over neural networks as tools. Neural networks also contain knowledge but in a different way. In a neural network, input values are fed into nodes, which calculate an output which is fed other nodes, or fed back into earlier nodes or taken as output. Knowledge is encoded in the weights given to different inputs to the nodes and by adjusting the weights you can \u201ctrain\u201d the system to recognize something in the inputs. These systems are capable of doing tasks, very well and very quickly, but it\u2019s difficult (or impossible) to describe any of the knowledge, so it wasn\u2019t very interesting for our purposes.<\/p>\n\n\n\n
That lack of knowledge description, or the system\u2019s ability to describe how it arrived at the answer it did, is something of a problem. If I ask a rule based system why it applied the rule it did, it can show input values and equations and how rules where processed and tested. A neural network can\u2019t don\u2019t that (and neither, really, can a human mind, whose neurons are the model for the neural network). This is fine, but it does mean that there\u2019s no solutions when odd behaviour happens like when an image identifier which is trained to recognize cats also recognizes certain patterns of static as cats as well. There\u2019s nothing we can do to sift out how that happened and even if we train the system again we can\u2019t be sure that there are other things where the system will be absolutely 100% convinced that the picture is of a cat.<\/p>\n\n\n\n
None of that is a real problem, but it was never where my interests lay. My PhD was focused on ways to build decentralised networks of agents to help do tasks (like figure out when your alarm clock needs to go off to get you to work on time based on the weather). Meanwhile computing got faster, a lot of problems were redesigned so that a GPU could solve them by doing a lot of identical math quickly. The world entered into an AI summer focused around neural network based machine learning and we had large neural network systems like AlphaGo suddenly performing complicated tasks quite well, based largely on the amount of computing we now had to throw at them. <\/p>\n\n\n\n
ChatGPT<\/h1>\n\n\n\n
Large language models, which include GPT (Generative Pre-trained Transformer) also snuck up on me. These contain, for a given bit of text, a probabilistic model for what text might come next. The modern versions read terabytes of information and use them to calculate those probabilities and part of what makes GPT3 the current model (excluding the chat part) work as well as it does is that it uses very large bits of text, around about 2000 words at a time. When you ask these systems to write something, they\u2019ll take some seed text and then see what words, probabilistically, should come next.<\/p>\n\n\n\n
I suspect, although I don\u2019t know, that the \u201ccorrectness\u201d of the output depends a lot on the frequency of phases and phrase structures appearing correctly in the training set. I think this is why things like introductory computer science questions are answered fairly well, with specific answers where as things like discussion around something like research design tends to be quite vague and generic and why on some topics the text is nonsense. The modern systems at least improve the overall coherence to earlier systems like Eliza<\/a> and Alice<\/a>.<\/p>\n\n\n\n Still however coherent and correct, it\u2019s important to keep in mind that there\u2019s no knowledge in the ChatGPT mechanism and no mechanism to monitor the quality of the output. In human terms, if you\u2019ve ever found yourself speaking out loud saying something surprising, that\u2019s pretty much the state GPT is always in. <\/p>\n\n\n\n It\u2019s worth noting that the chat in ChatGPT comes from a second model which they trained on example chats. Trainers wrote examples consisting of both sides of the type interaction they would like ChatGPT to have and then trained the system on those examples to teach the system to interact with people. Again I think the larger bits of text helps ChatGPT sound less disjointed than older chat bots, but I think this layer of training also leads to the extreme confidence in its responses that makes a lot of people uncomfortable with ChatGPT. <\/p>\n\n\n\n When I create art, a lot of what I enjoy doing is responding against randomness in the medium I\u2019m working in, scribbles or paint splotches into pictures, or stencils creating shapes against random backdrops, so I understand the urge to use ChatGPT as a starting point to spark creativity. <\/p>\n\n\n\n I\u2019m not sure at the end of the day that there\u2019s a lot of real benefits to incorporating it into teaching. I\u2019m not sure that it\u2019s capable (at least in it\u2019s current form) of generating sufficiently interesting material as a starting point for creativity, or of generating sufficently correction information for a student to respond to. If you ask it to suggest some starting points for stories, the results are uninspiring and sound a lot like a lot of plots that are passe because ChatGPT is trained on literature which has already been written.<\/p>\n\n\n\n I asked ChatGPT to create prompts for short stories and mixed media applications:<\/p>\n\n\n\n All of these are reasonable, and I could imagine them being given in a class context. I had hoped for something I\u2019d be inspired by. Certainly none of these make me excited, and while I may just need to learn the skill of prompting the AI better, I think I\u2019d rather go write and paint.<\/p>\n\n\n\n It\u2019s also interesting to see given the same prompt, ChatGPT produces a remarkably consistent response. <\/p>\n\n\n\n Looking at a lot of what\u2019s been written on ChatGPT in Higher Education, there\u2019s a general form of, \u201cTalk about Academic Integrity with your Students,\u201d \u201cTalk about ChatGPT,\u201d \u201cCreate and assessment that encourages students to intellectually engage with ChatGPT.\u201d I like the assignment Fyfe (Fyfe, 2022) uses where he has students try to write with GPT generated text, which they submit as an undifferentiated piece along with a reflection on how the work affected them. I think there\u2019s a benefit to getting students to engage, but that course was on engaging with these kinds of technologies. I\u2019m not sure the effect is as good if you\u2019re teaching a second year biology course. (If you are teaching a second year biology course, I\u2019d love to chat!)<\/p>\n\n\n\n I have suggested something similar for teaching computer science. Have students work with GPT (or some of the more code-focused Large Language Models) to generate a solution, then have the stutents test and correct ChatGPTs work, then report to the instructor what they learned. I think this gives the student a chance to really think about why code works, but I worry that starting with a coder that\u2019s not able to understand either what the code is supposed to do or why it works may not be good for student\u2019s learning.<\/p>\n\n\n\n By design, ChatGPT and LLMs are knowledge free. They\u2019re designed to take a corpus of text and determine for any particular chunk of text what other text probabilistically comes next. This produces text, and as I keep arguing, if the probable answers are correct, then the text is probably correct, but the correctness is not inherent in the model and in fact isn\u2019t a part of the model.<\/p>\n\n\n\n I think we\u2019ll see later versions of GPT and LLMs get better and better and produce more specific text. We may also see it produce more interesting text. The growth in image producing systems has certainly improved the quality over what was available even a year ago. I don\u2019t think at the end of the day that we\u2019ll see a really major change to art for a bit.<\/p>\n\n\n\n To grow, I think the system needs an underlying structure for knowledge. Understanding that a cat is a thing is going to be necessary to produce systems that are going to be able to do more than just talk<\/em> about things. I expect that at some point relatively soon we\u2019ll see some combination of an LLM with a Semantic Net<\/a> model like IBM\u2019s Watson<\/a> and then we might be able to start taking these systems at least a little seriously.<\/p>\n\n\n\n From a higher education perspective, I\u2019m very drawn to John Warner\u2019s<\/a> call to Make the work worth doing<\/a>. <\/strong>What I think ChatGPT illustrates is that a lot of the things we ask people to do when they learn are rote and default. We pick them because they\u2019re easy to explain and easy to mark. <\/p>\n\n\n\n I think the real wake up call here, is to create learning experiences that are relevant to the real students in the room with you right now. Build trust with them and show that you trust them. Let them participate in defining what they need to learn and how they\u2019re going to evaluate what they\u2019ve learned. You\u2019ll have to support them in that process, navigating their own learning and the things they can learn, but if they\u2019re doing the work they want to do then they\u2019re not thinking about how they can get around the system.<\/p>\n\n\n\n <\/p>\n\n\n\nAI and Creativity<\/h1>\n\n\n\n
![\"A](\"https:\/\/lh3.googleusercontent.com\/s_rceCcuu1v0xWv90hE6KO8ss4wvtBhEcOkWel0yW1Fr_lMRHtBR4_wKwZtQFcZLsMHc2fGbwp50yq0TlpAC18ogv5OzB52lsZhjqagDV4HSGKcxTyHvLVUMZCd42XhIygLOatJQyidzNyc8d8JN4uHQ-C_GplkNwDQAi5o_1B64V_5Tmgetfjti-G9Hjw\")
![\"A](\"https:\/\/lh5.googleusercontent.com\/teAN2vo5YSlNjtlucVBdhxIS6dvFCvDc0nwX8GqagDzwt8G3fEyCFHqBAhXmppI88SvWvp53t3UXv71uqqCyDbjlAbByzpYH6I3a3jwePV05o90pSc0-dGHSeqKd9mxWe6xmF1Ma_hy2SqMTb7e_shqwZmF90xAMEGRxk5b9zMlD1Mnh6LeVqqK_LSVCBQ\")
![\"Prompts](\"https:\/\/lh3.googleusercontent.com\/5qwHclS7Tg49NI3Sf_CvkrvWEoYtaW_k0XIcQDRfFagceSQXoBnpe-Ozg7p0ouFv1aOexD40lFRLGqovHhmp-5vXwR7VVTAtI4tnpm418ACdULunhmp_NrtL0qplOjTrEgDJr_gCwgyxabS5bTW1Z8v1EWsrOBI2-9PUkYPLKrVK5Xk2nu3mU9Wk8JfJ6w\")
Teaching in the age of ChatGPT<\/h1>\n\n\n\n