{"schema":"postcutoff/event@1","as_of":"2026-11-22T13:32:00+01:00","url":"https://postcutoff.com/e/2026-10-02-kls-conjecture-proved-ai-assisted/","md":"https://postcutoff.com/e/2026-10-02-kls-conjecture-proved-ai-assisted/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-10-02-kls-conjecture-proved-ai-assisted","date":"2026-10-02","date_precision":"day","short_title":"Kannan–Lovász–Simonovits conjecture proved in two AI-assisted preprints","deck":"Song–Zhang's O(1) bound, then Bizeul–Klartag–Lehec ('most proofs … found by ChatGPT')","takeaway":"The KLS conjecture (1995), which says isoperimetry in convex bodies is governed up to a universal constant by half-spaces, was claimed resolved twice in three days.","category":"science","category_label":"Science & math","importance":5,"confidence":"medium","status":{"key":"pending","labels":["Awaiting review"]},"sources":[{"n":1,"title":"arXiv 2610.01447: An O(1) Bound for the KLS Constant (Song, Zhang)","url":"https://arxiv.org/abs/2610.01447","type":"paper","group":"primary","domain":"arxiv.org"},{"n":2,"title":"arXiv 2610.05474: Presenting a proof of the Kannan-Lovasz-Simonovits conjecture (Bizeul, Klartag, Lehec)","url":"https://arxiv.org/abs/2610.05474","type":"paper","group":"primary","domain":"arxiv.org"},{"n":3,"title":"ETH Randomstrasse101: The KLS Conjecture (problem 30)","url":"https://randomstrasse101.math.ethz.ch/posts/KLSConjecture/","type":"discussion","group":"reactions","domain":"randomstrasse101.math.ethz.ch"}],"official":2,"filed":"2026-10-06","updated":"2026-10-13","orgs":["Microsoft Research","Weizmann Institute of Science","OpenAI","Anthropic"],"title":"Kannan–Lovász–Simonovits (KLS) conjecture proved in two AI-assisted preprints: Song–Zhang's O(1) bound, then Bizeul–Klartag–Lehec ('most proofs … found by ChatGPT')","summary":"The KLS conjecture (1995), which says isoperimetry in convex bodies is governed up to a universal constant by half-spaces, was claimed resolved twice in three days. Zhao Song and Xinzhi Zhang (arXiv 2610.01447, Oct 2; v2 Oct 4) prove an O(1) bound on the KLS constant with GPT-6 Astra, GPT-5.6 Sol and Claude Fable 5/5.1 after exploring 100+ approaches. Pierre Bizeul, Boaz Klartag and Joseph Lehec (arXiv 2610.05474, Oct 4) \"present a proof\" built on Song–Zhang's criterion, saying most proofs and ideas in it were found by ChatGPT.","key_facts":["Song & Zhang, 'An O(1) Bound for the KLS Constant', arXiv 2610.01447 (math.PR), Oct 2, 2026, v2 Oct 4: 'We prove that ψ_n ≤ C for a universal constant C > 0, resolving the KLS conjecture'; also a universal Poincaré constant for isotropic log-concave measures","Song–Zhang disclosure: 'The AI tools used in this work were GPT-6 Astra, GPT-5.6 Sol, Claude Fable 5, and Fable 5.1.' From July 28, 2026 they explored 'more than 100 approaches in collaboration with AI tools' to improve a log^(1/4) bound (from a paper that appeared on July 27, 2026) to log^(1/6); on Sept 30 the authors found a route to an f(log* n) bound, then sharpened it to a constant. 'All of the proofs have been carefully verified by the authors and several AI tools.'","Bizeul, Klartag & Lehec, 'Presenting a proof of the Kannan-Lovasz-Simonovits conjecture', arXiv 2610.05474, Oct 4: 'The crucial step in the proof is the very recent criterion from Song and Zhang involving high-order derivatives of tilt averages'","Bizeul–Klartag–Lehec disclosure: 'Most proofs and mathematical ideas in this paper were found by ChatGPT; a notable exception is the idea to use suspension which was suggested by the authors. The role of the authors has been mostly to understand these proofs and improve their exposition.' Their introduction says the conjecture now 'poses little challenge for contemporary AI tools'","Background: Klartag and Lehec had earlier proved a polylog bound and (with others) resolved Bourgain's slicing problem; KLS implies the slicing and thin-shell results","Verification status: two preprints, not peer-reviewed, no formal proof; Klartag–Lehec's independent write-up is a strong expert signal (confidence medium until reviewed)"],"key_numbers":[],"tags":["mathematics","convex-geometry","probability","kls","isoperimetry","gpt-6-astra","claude-fable","ai-discovery"],"science":{"field":"mathematics","subfield":"high-dimensional convex geometry / probability","problem":"Kannan–Lovász–Simonovits conjecture (universal Cheeger/Poincaré constant for isotropic log-concave measures)","result":"Universal O(1) bound on the KLS constant ψ_n (Song–Zhang); a second, AI-generated proof via Song–Zhang's criterion (Bizeul–Klartag–Lehec)","open_since":"1995","ai_system":["GPT-6 Astra","GPT-5.6 Sol","Claude Fable 5","Claude Fable 5.1","ChatGPT"],"human_role":"AI-assisted (Song–Zhang: human-chosen approaches, AI co-developed); largely AI-generated (Bizeul–Klartag–Lehec: authors mainly understood and exposited ChatGPT's proofs)","verification":{"key":"preprint","label":"Preprint only","text":"Two preprints; expert authors; not peer-reviewed or formalized"},"status":"pending","shock":"A central conjecture of asymptotic convex geometry fell within days to two AI-assisted teams, and leading experts wrote that it 'poses little challenge for contemporary AI tools'."},"body_md":"## What happened\n\nKLS asks for a dimension-free isoperimetric constant for convex bodies. Since Eldan's stochastic localization (2013), bounds improved\nfrom polynomial to polylogarithmic (Chen; Klartag–Lehec; Klartag). Song and Zhang, working with OpenAI and Anthropic models since late\nJuly, posted a proof of about 138 pages of an O(1) bound on Oct 2. Two days later Bizeul, Klartag and Lehec, among the area's leading experts,\nposted a shorter proof built on Song–Zhang's criterion, written mostly by ChatGPT.\n\n## Why it matters\n\nKLS was among the best-known open problems in high-dimensional geometry, with consequences for sampling algorithms on convex bodies. The\nsame week saw AI-originated proofs of the linear Hadwiger conjecture and a refutation of the 3SUM/APSP hypotheses. Confidence is medium\nonly because neither paper has been refereed or formalized yet.","disputed":[{"label":"Verification","text":"Two preprints; expert authors; not peer-reviewed or formalized","sources":[]}],"related":[{"id":"2026-10-13-ai-assisted-results-october-2026","url":"https://postcutoff.com/e/2026-10-13-ai-assisted-results-october-2026/","date":"2026-10-13","date_precision":"day","short_title":"October 2026: the arXiv stream of conjectures settled with disclosed AI help continues","deck":null,"takeaway":"In the first nine days of October 2026 the stream did not slow down: each arXiv listing brought several named conjectures with a disclosed AI role, and two new patterns appeared.","category":"science","category_label":"Science & math","importance":3,"confidence":"medium","status":{"key":"pending","labels":["Awaiting review"]},"sources":17,"official":17,"filed":"2026-10-13","updated":"2026-10-29","orgs":["OpenAI","Anthropic","Google DeepMind","various mathematicians"]},{"id":"2026-10-04-linear-hadwiger-conjecture-proved-gpt-6-astra","url":"https://postcutoff.com/e/2026-10-04-linear-hadwiger-conjecture-proved-gpt-6-astra/","date":"2026-10-04","date_precision":"day","short_title":"Linear Hadwiger conjecture proved","deck":"K_t-minor-free graphs are O(t)-colourable; proof found by GPT-6 Astra (Norin & Steiner), Lean-verified by Codex","takeaway":"With the 3SUM/APSP refutation and the KLS proofs posted the same week, it marks a step change in AI-originated mathematics: famous problems now fall with proofs largely written by models and checked by machines.","category":"science","category_label":"Science & math","importance":5,"confidence":"high","status":{"key":"pending","labels":["Event confirmed","Awaiting review"]},"sources":2,"official":2,"filed":"2026-10-06","updated":"2026-10-19","orgs":["OpenAI","McGill University","ETH Zurich"]},{"id":"2026-10-02-epsilon-dvoretzky-conjecture-klartag-moshe","url":"https://postcutoff.com/e/2026-10-02-epsilon-dvoretzky-conjecture-klartag-moshe/","date":"2026-10-02","date_precision":"day","short_title":"Klartag and Moshe prove the ε-Dvoretzky conjecture","deck":"The key probabilistic idea came from a ChatGPT discussion","takeaway":"This is a classical problem in asymptotic geometric analysis, and the preprint comes from Boaz Klartag (Tel Aviv University and Weizmann Institute), a leading researcher in the field.","category":"science","category_label":"Science & math","importance":4,"confidence":"high","status":{"key":"pending","labels":["Event confirmed","Awaiting review"]},"sources":1,"official":1,"filed":"2026-10-05","updated":"2026-10-05","orgs":["Tel Aviv University","Weizmann Institute of Science","OpenAI"]},{"id":"2026-07-25-sharp-thin-shell-inequality-gpt-5-6-pro","url":"https://postcutoff.com/e/2026-07-25-sharp-thin-shell-inequality-gpt-5-6-pro/","date":"2026-07-25","date_precision":"day","short_title":"Sharp thin-shell inequality","deck":"Var(|X|²) ≤ 8n for isotropic log-concave vectors, with a proof 'found by GPT-5.6 Pro' (Chen & Klartag)","takeaway":"This is a sharp result in a mature area, signed by people who built that area, with the model credited for the proof in the abstract.","category":"science","category_label":"Science & math","importance":3,"confidence":"high","status":{"key":"pending","labels":["Event confirmed","Awaiting review"]},"sources":3,"official":2,"filed":"2026-10-13","updated":"2026-10-13","orgs":["ETH Zurich","Weizmann Institute of Science","OpenAI"]}],"people":[{"id":"boaz-klartag","name":"Boaz Klartag","url":"https://postcutoff.com/person/boaz-klartag/"}],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-10-13","type":"edit","text":"Related: added the July sharp thin-shell inequality of Chen and Klartag (proof found by GPT-5.6 Pro), now its own entry"},{"date":"2026-10-13","type":"edit","text":"Related: the catalogue that lists this result is now [October 2026: the arXiv stream of conjectures settled with disclosed AI help continues](https://postcutoff.com/e/2026-10-13-ai-assisted-results-october-2026/) (the October blocks were split out of the summer catalogue)"},{"date":"2026-10-06","type":"filed","text":"Created (arXiv scan; both PDFs read with pdftotext)"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-06","run":null,"sources_read":"ArXiv scan; both PDFs read with pdftotext","updated":"2026-10-13","human_review":null,"version":{"date":"2026-10-13"}},"gaps":[{"model_id":"gpt-6-2-astra","name":"GPT-6.2 Astra","cutoff":"2026-05","days_after":124,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":94,"in_training_data":false},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":185,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":124,"in_training_data":false}],"short_url":"https://postcutoff.com/s/kannan-lovasz-simonovits"}