Latest
  1. Visa benchmark finds AI shopping agents fail 42.8% of runs
  2. OpenAI releases GPT-6 Cyber for approved security customers
  3. Google releases Gemini Omni 1.2 Flash with 15-second video clips
  4. Sierra acquires Anon to give its AI agents browser access
  5. Shield AI to buy counter-drone radar maker Echodyne for $5.3 billion
  6. Dropbox agrees to buy Tigris Data for $350m to expand its AI infrastructure
  7. About 600,000 Nvidia H200 chips are stored in Hong Kong awaiting Chinese approval
  8. Anthropic’s compute costs rose to 58% of revenue in Q3, its IPO filing shows

Latest / Frontier models and safety

ResearchFrontierUSConfirmed

Anthropic says Claude proved 123 open-source libraries free of crashes at the machine-code level

See how this story connects

Source: Anthropic

Anthropic’s Frontier Red Team, with the company Theorem, used Claude to write formal proofs that 239 entry points across 123 OSS-Fuzz libraries never crash on any input up to 64 MB, with proofs about compiled RISC-V binaries checked by the Rocq proof assistant. The proofs run to about 180 million lines of Rocq. While writing them, Claude found and patched bugs that had escaped years of fuzzing with trillions of test runs. Anthropic is publishing a subset of the proofs and the RISC-V and operating-system semantics, and Theorem offers to run the pipeline for other open-source projects.

Why it matters

Claude wrote machine-checked proofs for 123 libraries and found bugs that trillions of fuzzing runs had missed.

When
22 Oct 2026
ID
WTA-N-2026-0514
Who
Anthropic, Theorem

Summary written with AI by wheresthe.ai, from Anthropic. Checked against the source on 29 Oct 2026.

Read the original at Anthropic

Source copy: saved on 29 Oct 2026 to check this story and not republished, because the text belongs to its publisher. Document the source offers: document 1 (PDF). Also held by the Internet Archive.

Next stop on this Storyline: What happened nextAnthropic’s unreleased model chained flaws into working exploits for Chrome, Safari, Android, Windows and Linux

Cite this story

WTA-N-2026-0514: “Anthropic says Claude proved 123 open-source libraries free of crashes at the machine-code level.” wheresthe.ai, 22 Oct 2026. https://wheresthe.ai/d/anthropic-claude-formal-verification-123-libraries-2026-10/ (source: Anthropic).

Spotted an error? Email [email protected].