DeepMind's AlphaProof Code proves Signal's security properties on the compiled machine code
AI agents wrote about 6.5 million lines of Lean proving that libsignal's compiled AArch64 code keeps Signal's security promises. Humans approved the specs.
Topic · 12 stories
12 stories tagged lean on AI Tamer, newest first.
AI agents wrote about 6.5 million lines of Lean proving that libsignal's compiled AArch64 code keeps Signal's security promises. Humans approved the specs.
PSI published a Lean-checked proof of a 2008 quantum query conjecture, found by its system on an unnamed Anthropic model. Experts are still reading it.
FlashProve attaches a zero-knowledge proof to LLM output so a user can check which committed model produced it. Prototype only: 1,024 tokens, ~70-95x GPU cost.
Axiom Math released a sorry-free Lean proof of the classification of finite simple groups, built by agent swarms, and says it found 34 notable deviations.
OpenAI claims three new AI results, including a refutation of ETH, now public on GitHub with a Lean proof. None is peer reviewed, and its math advisers object.
A 17 October guest post on Terence Tao's blog proposes a math journal that requires proofs formally verified in Lean, citing errors in LLM-assisted proofs.
Tao says Open Math OS is soft-launched with DeepSeek V4.1 Flash, Kimi K3, and GLM 5.3 Flash on donated compute. Free academic accounts are still being granted.
Shanghai AI Lab says Intern-S2 helped on a 3D Ghys case. Zhang's preprint states a codimension-one theorem. Lean checks four theorems, one hypothesis open.
A King's College London and Cambridge preprint argues that OpenAI's Lean files for a Navier-Stokes blow-up proof do not match the English argument. The authors do not judge whether that English proof is correct.
doubleAI's October 2026 paper states an 8/5 girth constant for explicit regular graphs, above the 1988 bound of 4/3. The PDF is not a journal article. Ctech says the company puts the compute under $2,000.
OpenAI's math repository withdrew three manuscripts after a sign error, revised 14 others, and updated citations in 13 more. The README now lists 719 manuscripts, with 300 of 719 top-line results Lean-formalized.
OpenAI's GitHub catalogue lists 722 math manuscripts in 372 families from an unreleased internal model. Not all have Lean checks, and OpenAI says some unformalized results could have issues.