Skip to content

Anthropic Claims Claude Proved 239 Fuzzing Entry Points in 123 Libraries Never Crash

Oct 23, 2026
anthropic.com
Article image for Anthropic Claims Claude Proved 239 Fuzzing Entry Points in 123 Libraries Never Crash

Summary

Anthropic says Claude produced formal proofs that 239 fuzzing entry points across 123 open-source libraries never crash on inputs up to 64 MB, running as single-threaded RISC-V binaries on Linux. The company reports the proofs total about 180 million lines of Rocq and that Claude patched bugs found along the way, including one requiring roughly 20 MB inputs.

Key Points

  • Anthropic says a typical proof runs about 600,000 lines of Rocq for binaries with a median 18,000 RISC-V instructions.
  • Collaborator Theorem offers to run the same verification pipeline for other open-source projects, Anthropic says.
  • Anthropic reports agents sharing a proof workspace need 17% fewer tokens than agents working alone.

Tags

Read Original Article