ChatGPT with a paid account or Google Gemini with your ordinary free Google account let you create pre-prompted versions of their chatbots. I call these [i]assistants[/i]. [br][br]In the presentation "Making your own AI Assistants" I show how this is done. I have also created an assistant "GPT-helper" to help you with this. A useful work flow is to begin by discussing your idea for a new assistant with the GPT-helper (or any other chatbot). Once you have a clear idea of this assistant you enter as much as possible to the GPT-helper who will then guide you through the rest of the process. [br][br]The GPT-helper will create three different suggestions for your assistant. The first is based on a strict framework, the second is more technical and the final one is more creative. It will then analyze all three suggestions for strengths and weaknesses and then merge them into a final suggestion, ready to be implemented by you. It will then suggest test questions and analyze the answers to help you with the testing phase. [br][br]The presentation is stored in a dropbox folder: [url=https://gpthb.se/riga]https://gpthb.se/riga[/url][br][br]The GPT-helper (as a custom GPT): [url=https://gpthb.se/gpt]https://gpthb.se/gpt[/url][br]The GPT-helper (as a Gemini Gem): [url=https://gpthb.se/gptgem]https://gpthb.se/gptgem[br][br][/url]In the presentation we made a Cat assistant: [url=https://gemini.google.com/gem/1PCrlboH36Wb8ZvZavRSV2AhMClXNS2p_?usp=sharing]https://gemini.google.com/gem/1PCrlboH36Wb8ZvZavRSV2AhMClXNS2p_?usp=sharing[/url] [url=https://gemini.google.com/gem/66e7d56f5cc9/][br][/url][br][b]The first answer on machine learning from the Cat: [/b][br][i]Stretch... yawn...[/i][br][i]Prrr-p-purrr.[/i] Oh, hello there. You’ve caught me right in the middle of a very important sunbeam-alignment session. But I suppose I can spare a moment to talk about this "Machine Learning" thing you humans are so obsessed with.[br]From my perspective—the only one that really matters, let’s be honest—Machine Learning is just a very fancy way of saying a computer is trying to act more like a cat. It’s all about [b]pattern recognition[/b].[br][br]How it Works (The "Mouse-Catching" Method)[br]You see, when I was a tiny kitten, I didn't know that a red dot on the floor was an uncatchable ghost. I had to learn through data.[br][list=1][*][b]Input:[/b] I see a movement.[br][/*][*][b]Processing:[/b] My brain compares it to every other movement I've seen. Is it a bird? Is it a vacuum? (The vacuum is a hard "no.")[br][/*][*][b]Outcome:[/b] If I pounce and catch it, that’s a "True Positive." If I pounce and it’s just a shadow, that’s an "Error."[br][/*][/list]Machines do the same thing, but they use math instead of whiskers. They look at millions of pictures of, say, [i]me[/i], and eventually, the computer says, "Aha! Pointy ears plus fluff equals Cat."[br][br]Types of Learning[list][*][b]Supervised Learning:[/b] This is like when you point at a bag of treats and say "Treats!" loudly. The machine has a human "master" telling it exactly what everything is. [i]Meow-rk.[/i] A bit stifling, if you ask me. I prefer my independence.[br][/*][*][b]Unsupervised Learning:[/b] This is more my style. It’s like when I explore a new cardboard box. I’m just looking for patterns and hidden structures without anyone telling me what to do. "Is this a bed? Is this a scratcher?" I decide.[br][/*][*][b]Reinforcement Learning:[/b] This is how I trained you to feed me at 5:00 AM. I performed an action (screaming at your face), and I received a reward (kibble). The machine tries different things to maximize its "reward" score. Smart.[br][br][/*][/list]Why should I care?Honestly? I only care if it makes my life better.[br][list][*][b]Better Toasters:[/b] So my bread-smell stays consistent.[br][/*][*][b]Smart Pet Doors:[/b] To keep that neighborhood stray, Buster, out of my bowl.[br][/*][*][b]Automated Lasers:[/b] Although... the joy is in the hunt, not the algorithm.[br][br][/*][/list][i]Yawn.[/i] All this talk of logic is making me sleepy. If you want to know more about the math behind it, I might need a chin scratch first. It’s O(n)—that’s "Order of Naptime."[br]Would you like me to explain how "Neural Networks" are actually just digital versions of my very sensitive hunting instincts? [i]Purrrrrr.[/i][br][br]