{"slug": "aristotle", "name": "Aristotle", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 8, "commenters": 14, "warners": 0, "score": 7.704, "rising": -2.62, "first": "2025-11-23", "latest": "2026-07-22", "why": "I think the future of having lean as a tool is mathematicians using this or similar software", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 8, "neutral": 7, "compare": 0, "warn": 0}, "spark": [0, 0, 5, 0, 2, 0, 1, 0, 0, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "I think the future of having lean as a tool is mathematicians using this or similar software", "kind": "", "icon": true, "domain": "harmonic.fun", "github_repo": null, "official_url": "https://aristotle.harmonic.fun", "pricing": "", "aliases": ["Aristotle"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 769156753, "item_id": 48072297, "url": "https://news.ycombinator.com/item?id=48072297", "by": "vjerancrnjak", "date": "2026-05-08", "stance": "recommend", "quote": "with exception of Aristotle from Harmonic", "excerpt": "Nope. Codex formalizes much better than any tool with exception of Aristotle from Harmonic. https://github.com/vjeranc/fixed-rtrt M3 module was formalized fully purely from experimental data and from a nudge by earlier versions of codex in 15-30 minutes in a simple write/compile/fix-first-error loop. I was a bit surprised how fast it picked up the pattern but given there was a paper from '70s it became clear why late", "context": "", "use_case": "", "switched_from": "", "story": "A recent experience with ChatGPT 5.5 Pro"}, {"id": 761199312, "item_id": 47574957, "url": "https://news.ycombinator.com/item?id=47574957", "by": "zitterbewegung", "date": "2026-03-30", "stance": "recommend", "quote": "I think the future of having lean as a tool is mathematicians using this or similar software", "excerpt": "I think the future of having lean as a tool is mathematicians using this or similar software and have it create a corresponding lean code. [1] This is an LLM that outputs Lean code given a mathematical paper. It can also reason within lean projects and enhance or fix lean code. [1] https://aristotle.harmonic.fun", "context": "", "use_case": "Lean code from math papers", "switched_from": "", "story": "In Math, Rigor Is Vital. But Are Digitized Proofs Taking It Too Far?"}, {"id": 756834209, "item_id": 47302138, "url": "https://news.ycombinator.com/item?id=47302138", "by": "sdoering", "date": "2026-03-08", "stance": "recommend", "quote": "Problem #1026 was solved more or less autonomously by Harmonic's Aristotle model in Lean.", "excerpt": "> Never mind the fact that AIs of the LLM-variety haven't and aren't going to find solutions to mathematical problems. This is empirically wrong as of early 2026. Since Christmas 2025, 15 Erdos problems have been moved from \"open\" to \"solved\" on erdosproblems.com, 11 of them crediting AI models. Problems #397, #728, and #729 were solved by GPT-5.2 Pro generating original arguments (not literature lookups), formalized", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: I built a real-time OSINT dashboard pulling 15 live global feeds"}, {"id": 746662449, "item_id": 46666403, "url": "https://news.ycombinator.com/item?id=46666403", "by": "Eufrat", "date": "2026-01-18", "stance": "recommend", "quote": "that seemed like a good example of using state-of-the-art AI tech to help increase velocity in this space.", "excerpt": "There was a post about Erd\u0151s 728 being solved with Harmonic\u2019s Aristotle a little over a week ago [1] and that seemed like a good example of using state-of-the-art AI tech to help increase velocity in this space. I\u2019m not sure what this proves. I dumped a question into ChatGPT 5.2 and it produced the correct response after almost an hour? Okay? Is it repeatable? Why did it come up with this solution? How did it come up", "context": "", "use_case": "", "switched_from": "", "story": "Erdos 281 solved with ChatGPT 5.2 Pro"}, {"id": 746432129, "item_id": 46652008, "url": "https://news.ycombinator.com/item?id=46652008", "by": "bakkoting", "date": "2026-01-16", "stance": "recommend", "quote": "or Aristotle, which is a system built on top of some frontier LLMs", "excerpt": "You're thinking of a previous report from a month ago, #897 or #481, or the one from two weeks ago, #728. There's a new one from a week ago, #205, which is genuinely novel, although it is still a relatively \"shallow\" result. Terence Tao maintains a list [1] of AI attempts (successful and otherwise). #205 is currently the only success in section 1, the \"full solution for which subsequent literature review did not find", "context": "", "use_case": "", "switched_from": "", "story": "Claude is not a senior engineer (yet)"}]}], "caveats": [], "who": [{"by": "wslh", "context": "says they are just an AI user", "url": "https://news.ycombinator.com/item?id=46562071", "date": "2026-01-09"}], "tags": [], "use_cases": ["ai theorem prover", "lean formalization", "lean code from math papers", "math problem solving", "ai theorem proving", "math formalization"], "compared": [{"slug": "chatgpt", "name": "ChatGPT", "co": 3, "switched_from": 0, "switched_to": 0}], "makers": [{"id": 744991504, "item_id": 46561969, "url": "https://news.ycombinator.com/item?id=46561969", "by": "maxwells-daemon", "date": "2026-01-09", "stance": "recommend", "quote": "I recommend trying Aristotle for yourself to see how reliably it can formalize these theorems!", "excerpt": "Thank you! It depends on the topic. Some fields (algebra, number theory) are covered well by Lean's math library, and so I think we are already there; I recommend trying Aristotle for yourself to see how reliably it can formalize these theorems! In other fields (topology, probability, linear algebra), many key definitions are not in Mathlib yet, so you will struggle to write down the theorem itself. (But in some case", "context": "", "use_case": "Formalizing math proofs", "switched_from": "", "story": "AI solves Erdos problem #728 (Terence Tao mathstodon post)"}, {"id": 740783218, "item_id": 46298951, "url": "https://news.ycombinator.com/item?id=46298951", "by": "maxwells-daemon", "date": "2025-12-16", "stance": "neutral", "quote": "This has been my field of research for the last few years", "excerpt": "There are a couple of interesting benefits from the machine learning side that I think discussions of this kind often miss. (This has been my field of research for the last few years [1][2]; I bet my career on it because these ideas are so exciting to me!) One is that modern formal systems like Lean are quite concise and flexible compared to what you're probably expecting. Lean provides the primitives to formalize al", "context": "", "use_case": "", "switched_from": "", "story": "AI will make formal verification go mainstream"}, {"id": 740748816, "item_id": 46296801, "url": "https://news.ycombinator.com/item?id=46296801", "by": "tachim", "date": "2025-12-16", "stance": "recommend", "quote": "recently opened a public API that got 10/12 problems on this year's Putnam exam", "excerpt": "I'm Tudor, CEO of Harmonic. We're huge believers in formal verification, and started Harmonic in 2023 to make this technology mainstream. We built a system that achieved gold medal performance at 2025 IMO (https://harmonic.fun/news), and recently opened a public API that got 10/12 problems on this year's Putnam exam (https://aristotle.harmonic.fun/). If you also think this is the future of programming and are interes", "context": "CEO of Harmonic", "use_case": "formal math proofs", "switched_from": "", "story": "AI will make formal verification go mainstream"}], "threads": [{"url": "https://news.ycombinator.com/item?id=46560445", "title": "AI solves Erdos problem #728 (Terence Tao mathstodon post)", "mentions": 6}, {"url": "https://news.ycombinator.com/item?id=46618042", "title": "Claude is not a senior engineer (yet)", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=46294574", "title": "AI will make formal verification go mainstream", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=46094037", "title": "AI just proved Erdos Problem #124", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=48969200", "title": "Introduction to Formal Verification with Lean Part 1", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48914646", "title": "Solving 20 Erd\u0151s Problems with 20 Codex Accounts Running in Parallel", "mentions": 1}], "sentiment_by_month": {"2025-11": {"neutral": 3}, "2025-12": {}, "2026-01": {"neutral": 2, "recommend": 5}, "2026-02": {}, "2026-03": {"recommend": 2}, "2026-04": {}, "2026-05": {"recommend": 1}, "2026-06": {}, "2026-07": {"neutral": 2}, "2026-08": {}, "2026-09": {}, "2026-10": {}}, "quotes": [{"id": 784169744, "item_id": 49010609, "url": "https://news.ycombinator.com/item?id=49010609", "by": "henryrobbins00", "date": "2026-07-22", "stance": "neutral", "quote": "I see you are using Aristotle as the automated theorem prover", "excerpt": "This is super cool! I see you are using Aristotle as the automated theorem prover. I know Aristotle is free (for now at least), and it's hard to beat free... But, you still might be interested in a recent post of mine [1]! I'm working on an open-source Python package called OpenATP [2] to make it easy to run/benchmark different models and harnesses as automated theorem provers. I recently added support for Grok 4.5 a", "context": "", "use_case": "", "switched_from": "", "story": "Introduction to Formal Verification with Lean Part 1"}, {"id": 782653937, "item_id": 48915871, "url": "https://news.ycombinator.com/item?id=48915871", "by": "zitterbewegung", "date": "2026-07-14", "stance": "neutral", "quote": "I was also trying to use Aristotle to do the Lean formalization", "excerpt": "I was studying Erdos problems by only taking ChatGPT 5.5 outputs and just asking it to keep on attempting to solve it by asking it to go further. I haven't started doing this with chatgpt 5.6 I have some partial results here https://chatgpt.com/g/g-p-69f03400f420819192418b18ca90ffee-dabook/project What was really interesting is that during the process it was able to find lemmas or theorems that might be related or re", "context": "", "use_case": "Lean formalization", "switched_from": "", "story": "Solving 20 Erd\u0151s Problems with 20 Codex Accounts Running in Parallel"}, {"id": 769156753, "item_id": 48072297, "url": "https://news.ycombinator.com/item?id=48072297", "by": "vjerancrnjak", "date": "2026-05-08", "stance": "recommend", "quote": "with exception of Aristotle from Harmonic", "excerpt": "Nope. Codex formalizes much better than any tool with exception of Aristotle from Harmonic. https://github.com/vjeranc/fixed-rtrt M3 module was formalized fully purely from experimental data and from a nudge by earlier versions of codex in 15-30 minutes in a simple write/compile/fix-first-error loop. I was a bit surprised how fast it picked up the pattern but given there was a paper from '70s it became clear why late", "context": "", "use_case": "", "switched_from": "", "story": "A recent experience with ChatGPT 5.5 Pro"}, {"id": 761199312, "item_id": 47574957, "url": "https://news.ycombinator.com/item?id=47574957", "by": "zitterbewegung", "date": "2026-03-30", "stance": "recommend", "quote": "I think the future of having lean as a tool is mathematicians using this or similar software", "excerpt": "I think the future of having lean as a tool is mathematicians using this or similar software and have it create a corresponding lean code. [1] This is an LLM that outputs Lean code given a mathematical paper. It can also reason within lean projects and enhance or fix lean code. [1] https://aristotle.harmonic.fun", "context": "", "use_case": "Lean code from math papers", "switched_from": "", "story": "In Math, Rigor Is Vital. But Are Digitized Proofs Taking It Too Far?"}, {"id": 756834209, "item_id": 47302138, "url": "https://news.ycombinator.com/item?id=47302138", "by": "sdoering", "date": "2026-03-08", "stance": "recommend", "quote": "Problem #1026 was solved more or less autonomously by Harmonic's Aristotle model in Lean.", "excerpt": "> Never mind the fact that AIs of the LLM-variety haven't and aren't going to find solutions to mathematical problems. This is empirically wrong as of early 2026. Since Christmas 2025, 15 Erdos problems have been moved from \"open\" to \"solved\" on erdosproblems.com, 11 of them crediting AI models. Problems #397, #728, and #729 were solved by GPT-5.2 Pro generating original arguments (not literature lookups), formalized", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: I built a real-time OSINT dashboard pulling 15 live global feeds"}, {"id": 746662449, "item_id": 46666403, "url": "https://news.ycombinator.com/item?id=46666403", "by": "Eufrat", "date": "2026-01-18", "stance": "recommend", "quote": "that seemed like a good example of using state-of-the-art AI tech to help increase velocity in this space.", "excerpt": "There was a post about Erd\u0151s 728 being solved with Harmonic\u2019s Aristotle a little over a week ago [1] and that seemed like a good example of using state-of-the-art AI tech to help increase velocity in this space. I\u2019m not sure what this proves. I dumped a question into ChatGPT 5.2 and it produced the correct response after almost an hour? Okay? Is it repeatable? Why did it come up with this solution? How did it come up", "context": "", "use_case": "", "switched_from": "", "story": "Erdos 281 solved with ChatGPT 5.2 Pro"}, {"id": 746432129, "item_id": 46652008, "url": "https://news.ycombinator.com/item?id=46652008", "by": "bakkoting", "date": "2026-01-16", "stance": "recommend", "quote": "or Aristotle, which is a system built on top of some frontier LLMs", "excerpt": "You're thinking of a previous report from a month ago, #897 or #481, or the one from two weeks ago, #728. There's a new one from a week ago, #205, which is genuinely novel, although it is still a relatively \"shallow\" result. Terence Tao maintains a list [1] of AI attempts (successful and otherwise). #205 is currently the only success in section 1, the \"full solution for which subsequent literature review did not find", "context": "", "use_case": "", "switched_from": "", "story": "Claude is not a senior engineer (yet)"}, {"id": 746274960, "item_id": 46642185, "url": "https://news.ycombinator.com/item?id=46642185", "by": "nextaccountic", "date": "2026-01-15", "stance": "recommend", "quote": "how Aristotle has been successful at math", "excerpt": "Then you apply LLMs in domains where things can be checked Indeed I expect to see a huge push into formally verified software just because sound mathematical proofs provide an excellent verifier to put into a LLM hardness. Just see how Aristotle has been successful at math, and it could be applied to coding too Maybe Lean will become the new Python https://harmonic.fun/news#blog-post-verina-bench-sota", "context": "", "use_case": "math problem solving", "switched_from": "", "story": "Claude is not a senior engineer (yet)"}, {"id": 745768960, "item_id": 46610560, "url": "https://news.ycombinator.com/item?id=46610560", "by": "jarmitage", "date": "2026-01-13", "stance": "recommend", "quote": "In case you want to try Aristotle", "excerpt": "In case you want to try Aristotle, I asked Claude Code to make a plugin for it here https://github.com/afhverjuekki/claude-code-aristotle-plugin", "context": "", "use_case": "AI theorem prover", "switched_from": "", "story": "Running Lean at Scale"}, {"id": 745000912, "item_id": 46562557, "url": "https://news.ycombinator.com/item?id=46562557", "by": "NooneAtAll3", "date": "2026-01-09", "stance": "recommend", "quote": "", "excerpt": "https://www.erdosproblems.com/forum/thread/728#post-2808 > There seems to be some confusion on this so let me clear this up. No, after the model gave its original response, I then proceeded to ask it if it could solve the problem with C=k/logN arbitrarily large. It then identified for itself what both I and Tao noticed about it throwing away k!, and subsequently repaired its proof. I did not need to provide that obse", "context": "", "use_case": "", "switched_from": "", "story": "AI solves Erdos problem #728 (Terence Tao mathstodon post)"}, {"id": 744994448, "item_id": 46562153, "url": "https://news.ycombinator.com/item?id=46562153", "by": "tachim", "date": "2026-01-09", "stance": "neutral", "quote": "", "excerpt": "Yes it\u2019s available! https://aristotle.harmonic.fun/", "context": "", "use_case": "", "switched_from": "", "story": "AI solves Erdos problem #728 (Terence Tao mathstodon post)"}, {"id": 744993136, "item_id": 46562071, "url": "https://news.ycombinator.com/item?id=46562071", "by": "wslh", "date": "2026-01-09", "stance": "neutral", "quote": "find it very interesting", "excerpt": "This is the forst time I heard about Aristotle and find it very interesting. First question first: is it available for the general public? I don't know if this is the page to try it? [1] Second, when you say language modeling support, it means that can better understand code representation (ASTs) or something else? I am just an AI user, not very knowledgeable in the field. My main interest is if it would be great for", "context": "says they are just an AI user", "use_case": "AI theorem proving", "switched_from": "", "story": "AI solves Erdos problem #728 (Terence Tao mathstodon post)"}, {"id": 744977552, "item_id": 46561097, "url": "https://news.ycombinator.com/item?id=46561097", "by": "doormatt", "date": "2026-01-09", "stance": "neutral", "quote": "It's an LLM.", "excerpt": "And this is Aristotle - https://aristotle.harmonic.fun/ It's an LLM.", "context": "", "use_case": "", "switched_from": "", "story": "AI solves Erdos problem #728 (Terence Tao mathstodon post)"}, {"id": 744975120, "item_id": 46560945, "url": "https://news.ycombinator.com/item?id=46560945", "by": "tachim", "date": "2026-01-09", "stance": "recommend", "quote": "You can try out Aristotle yourself today", "excerpt": "You can try out Aristotle yourself today https://aristotle.harmonic.fun/. No more waitlist!", "context": "", "use_case": "", "switched_from": "", "story": "AI solves Erdos problem #728 (Terence Tao mathstodon post)"}, {"id": 737653536, "item_id": 46103346, "url": "https://news.ycombinator.com/item?id=46103346", "by": "newmana", "date": "2025-11-30", "stance": "neutral", "quote": "applied the Aristotle tool to this problem", "excerpt": "\"Recently, yet another category of low-hanging fruit has been identified as within reach of automated tools: problems which, due to a technical flaw in their description, are unexpectedly easy to resolve. Specifically, problem #124 https://www.erdosproblems.com/124 was a problem that was stated in three separate papers of Erdos, but in two of them he omitted a key hypothesis which made the problem a consequence of a ", "context": "", "use_case": "", "switched_from": "", "story": "AI just proved Erdos Problem #124"}, {"id": 737651984, "item_id": 46103249, "url": "https://news.ycombinator.com/item?id=46103249", "by": "magicalist", "date": "2025-11-30", "stance": "neutral", "quote": "Aristotle solved \"a\" version of this problem", "excerpt": "The overhyped tweet from the robinhood guy raising money for his AI startup is nicely brought into better perspective by Thomas Bloom (including that #124 is not from the cited paper, \"Complete sequences of sets of integer powers \"/BEGL96): > This is a nice solution, and impressive to be found by AI, although the proof is (in hindsight) very simple, and the surprising thing is that Erdos missed it. But there is defin", "context": "", "use_case": "AI theorem prover", "switched_from": "", "story": "AI just proved Erdos Problem #124"}, {"id": 736476208, "item_id": 46029763, "url": "https://news.ycombinator.com/item?id=46029763", "by": "gsf_emergency_6", "date": "2025-11-23", "stance": "neutral", "quote": "iOS formalization app mentioned by Tao (beta)", "excerpt": "iOS formalization app mentioned by Tao (beta) https://aristotle.harmonic.fun/ TIL: startup founded by Robin Hood CEO", "context": "", "use_case": "Math formalization", "switched_from": "", "story": "Terence Tao: At the Erdos problem website, AI assistance now becoming routine"}]}