{"generated_at":"2026-11-12T18:35:06.992Z","source":{"name":"Hacker News public API","url":"https://github.com/HackerNews/API","attribution":"Stories and comments are public Hacker News submissions by their respective authors. HackerHub is an independent reader, not affiliated with Y Combinator.","content_is_untrusted":true},"story_id":50438261,"hn_url":"https://news.ycombinator.com/item?id=50438261","total_comments":131,"returned":20,"scope":"Up to the requested number of top-level comments in Hacker News ranked order. Deleted comments are omitted. Nested replies are not fetched; this is not the complete thread.","comments":[{"id":50466452,"author":"Tar90","created_at":"2026-11-12T12:56:06.000Z","text":"I've been experimenting with a lot of these learning skills (see also, e.g., https://github.com/mattpocock/skills/blob/main/skills/produc..., which I think addresses the progress tracking part better than this skill) and they're great for getting simple answers, getting unstuck on exercises, getting some intuition through simulations, etc, but I still feel some more structure is needed for effective self-teaching. Has anyone tried using a hard book as a sort of course structure and asking the LLM to teach you through it? You could of course just read the book, but a lot of advanced subjects don't have great learning materials.","parent_id":50438261,"replies_count":7,"hn_url":"https://news.ycombinator.com/item?id=50466452"},{"id":50464068,"author":"zkmon","created_at":"2026-11-12T07:23:04.000Z","text":"This is really cool. I think we will see more of these, inching towards 'refined' thought and expression percolating from AI models into human minds.\nI noticed that the quality of email text has gone up around my work these days. everyone is sounding like a master of drafting emails. Ofcourse Ai has a role in it. But real cool thing about this is, this is pulling up people's thinking to have a structure, minimalism and sequencing of expression. Same as how textile industry has enabled people to have an style and expression in clothing.","parent_id":50438261,"replies_count":12,"hn_url":"https://news.ycombinator.com/item?id=50464068"},{"id":50464568,"author":"genxy","created_at":"2026-11-12T08:38:27.000Z","text":"Socratic tutoring is the first thing I did when ChatGPT first shipped. Your liberal arts education is a \"huge unlock\" if you just apply it.\nSee also https://en.wikipedia.org/wiki/Mastery_learning\nhttps://en.wikipedia.org/wiki/Programmed_learning\nMake your own custom skinner boxes. https://en.wikipedia.org/wiki/Operant_conditioning_chamber","parent_id":50438261,"replies_count":2,"hn_url":"https://news.ycombinator.com/item?id=50464568"},{"id":50466754,"author":"pkoird","created_at":"2026-11-12T13:25:42.000Z","text":"Is it only me who's thinking what's so special about this and whys everyone oohing and aahing over this? Afaik, people I know (and me) we've been doing this ever since LLMs became capable enough.","parent_id":50438261,"replies_count":7,"hn_url":"https://news.ycombinator.com/item?id=50466754"},{"id":50464180,"author":"Mikhail_Edoshin","created_at":"2026-11-12T07:40:46.000Z","text":"Socratic questions are not asked blindly. They are meant to help the student to realize the incompleteness or falsety of what they think they know. That us, to realise they do not actually know something and thus put them into a position of not knowing, which is the only way to gain understanding.\nOne man said, that enlightement (as in Zen) cannot be faked. Whoever had it, will be able to tell if someone else had it or not. There is no way to merely sound like it. Socratic method is like enlightement.","parent_id":50438261,"replies_count":5,"hn_url":"https://news.ycombinator.com/item?id=50464180"},{"id":50465114,"author":"lemax","created_at":"2026-11-12T09:51:51.000Z","text":"I’ve struggled to get AI to teach me things well without spilling hints or giving answers away. Assuming this was built on some solid evals this could be awesome.\n> When the user is wrong, do not give the answer. Ask a narrower question that exposes the contradiction in their reasoning","parent_id":50438261,"replies_count":2,"hn_url":"https://news.ycombinator.com/item?id=50465114"},{"id":50464996,"author":"jan_m_savage","created_at":"2026-11-12T09:32:51.000Z","text":"Oh this is so good. I asked it to teach me programming in Logo; though the model is not the best (GLM 4.7, on pi), the tutor is asking very good questions and is not too pedantic about exact answers.\nFor those new (beginners), install pi from pi.dev and then your favorite AI model (ask your model how to set up pi and it). Then ask your pi-based AI how to set up the tutor (just give it this link, it will set it up for you).\nThen start pi by typing pi in the terminal; and to launch the tutor preface your question with: /skill:socratic-tutor. Like so:\n/skill:socratic-tutor teach me Python.","parent_id":50438261,"replies_count":0,"hn_url":"https://news.ycombinator.com/item?id=50464996"},{"id":50465521,"author":"koolba","created_at":"2026-11-12T10:57:48.000Z","text":"This is a cool idea. Though trying this out using the claude CLI is kind of funny because by default it's suggestion for the next prompt is the answer to the question.","parent_id":50438261,"replies_count":1,"hn_url":"https://news.ycombinator.com/item?id=50465521"},{"id":50467555,"author":"sigbottle","created_at":"2026-11-12T14:16:16.000Z","text":"I don't think a simple prompt will exceed any kind of memory system. Nothing fancy, but you need the agent to tune to your quirks; I find that a prompt to try and distill everything a priori is too annoying.\nBeen just using less of chat recently and using more codex for learning - a direct shared interactable terminal is nice, it's still relatively cheap, and importantly you can log specific thoughts to say a git repo for memory.\nIt's not attempting to be some kind of knowledge ontology graph like many businesses want - you just want it to understand the specific quirks of your specific learning path, which may not be formalizable or worth be spending time to step back and formalize every little thing.","parent_id":50438261,"replies_count":0,"hn_url":"https://news.ycombinator.com/item?id=50467555"},{"id":50466904,"author":"bsenftner","created_at":"2026-11-12T13:38:14.000Z","text":"I've written an entire Socratic AI based office suite with project management and media creation, current count over 1500 agents:\nhttps://midombot.com/b1/home\nIt's comprehensive, it was written at an immigration law firm, so it has all kinds of language and other perspective understanding tools, as well as a complete media suite to aid in the creation of visual explainers, courseware, and marketing media.\nhttps://midombot.com/b1/blog/MI/method-intelligence-presents...","parent_id":50438261,"replies_count":0,"hn_url":"https://news.ycombinator.com/item?id=50466904"},{"id":50438436,"author":"orbis-tertius","created_at":"2026-11-10T10:41:26.000Z","text":"I love the idea but Jane Street might have copied (or independently rediscovered) https://github.com/bevibing/socrates-skill","parent_id":50438261,"replies_count":2,"hn_url":"https://news.ycombinator.com/item?id=50438436"},{"id":50471816,"author":"casey2","created_at":"2026-11-12T18:25:17.000Z","text":"Rather than saying stuff like 4-10 or 3-5, make that an explicit program (rng) and tell it to add or subtract based on a decision. Otherwise it is very likely to just always pick the same number.","parent_id":50438261,"replies_count":0,"hn_url":"https://news.ycombinator.com/item?id=50471816"},{"id":50464688,"author":"Imanari","created_at":"2026-11-12T08:54:01.000Z","text":"Socratic tutoring with LLMs works great for me and I have used this skill and it also works great (can you do the same with a simple prompt? probably)\nUsing LLMs this way was really refreshing, I could really feel how I started to think on my own again.","parent_id":50438261,"replies_count":1,"hn_url":"https://news.ycombinator.com/item?id=50464688"},{"id":50468747,"author":"brlewis","created_at":"2026-11-12T15:16:12.000Z","text":"As someone with a superficial understanding of how LMs work, I'm surprised that the ASCII art part of the skill can work. I guessed that the harness has to get involved there, as ASCII art generation looks to me like a different task than next-token generation. Can a knowledgeable human add any detail?\nI asked Gemini and at first it claimed that generating ASCII art is business as usual for the harness and the LM. It didn't give any convincing evidence. I asked it to steel-man the opposite position, and after that asked for its current thinking. It had convinced itself of the opposite, but still no definitive sources.","parent_id":50438261,"replies_count":1,"hn_url":"https://news.ycombinator.com/item?id=50468747"},{"id":50464352,"author":"arshxyz","created_at":"2026-11-12T08:06:56.000Z","text":"Been using this with Opus 5.5 on Medium for a week or so. I've used the same model for learning before and I definitely prefer using this skill because it stops the model from the usual handholding. Although I'd say most of the effect can be replicated with this line: \"When the user is wrong, do not give the answer. Ask a narrower question that exposes the contradiction in their reasoning.\"","parent_id":50438261,"replies_count":0,"hn_url":"https://news.ycombinator.com/item?id=50464352"},{"id":50468975,"author":"TonyAlicea10","created_at":"2026-11-12T15:27:48.000Z","text":"No matter how many of these are tried (and I’ve tried making many iterations), LLMs are generally terrible at building a progressive curriculum.\nThey inevitably structure things poorly, often including topics before they’re fully explained later.\nThe bigger the curriculum the worse it gets. They can be amazing once a human instructor provides an outline but not from scratch.","parent_id":50438261,"replies_count":1,"hn_url":"https://news.ycombinator.com/item?id=50468975"},{"id":50464050,"author":"poilcn","created_at":"2026-11-12T07:19:25.000Z","text":"what am i missing, why does it have 434 forks and 6.3k starts? is it botted? what's the point","parent_id":50438261,"replies_count":3,"hn_url":"https://news.ycombinator.com/item?id=50464050"},{"id":50468359,"author":"bemtevi","created_at":"2026-11-12T14:56:18.000Z","text":"If these become really good, I think it's sad that people will interact with other people less and less and just learn from machines. It might make people smarter and more well-versed in some arcane topic, but I wonder if that will make the world a better place? I think probably not.","parent_id":50438261,"replies_count":1,"hn_url":"https://news.ycombinator.com/item?id=50468359"},{"id":50465672,"author":"amelius","created_at":"2026-11-12T11:22:06.000Z","text":"I want an AI that I can give a paper, and then sits with me to understand it, maybe even implement it (though this is the easy part for the LLM).","parent_id":50438261,"replies_count":2,"hn_url":"https://news.ycombinator.com/item?id=50465672"},{"id":50464730,"author":"nilsherzig","created_at":"2026-11-12T08:59:13.000Z","text":"someone at jane street likes https://www.mathacademy.com/how-it-works","parent_id":50438261,"replies_count":0,"hn_url":"https://news.ycombinator.com/item?id=50464730"}]}