Claude produced machine-checked proofs for 239 fuzz entry points across 123 libraries
kieranklaassen · x · 2026-11-12
Serokell analyzes Anthropic's Oct 22 report from its Frontier Red Team and Theorem: in a few weeks, Claude generated machine-checked proofs that 239 fuzz-test entry points across 123 open-source libraries never crash on any input under 64 MB, reasoning directly over compiled RISC-V binaries in a modeled Linux environment. Claude also found and patched bugs that had survived trillions of fuzzing runs.
Key points
- Formal verification proves a property for all inputs, unlike testing
- Generated proofs differ from generated code: proofs are machine-checked, so the usual human-review burden for LLM "slop code" doesn't apply the same way
- As AI code generation gets cheaper, formal proofs become feasible far beyond mission-critical software
More from coding & agent
- United Airlines to Ban Personal AI Agents From Booking Flights for Customers — Polymarket · 2026-11-12
- Agentic Search explained: a 4-search loop costs about 5x one search — and queries leak to more companies — adnan_hashmi · 2026-11-12
- AWS says thousands of autonomous AI agents wrote every line of AWS Emulator — SumitGup · 2026-11-12
- freeCodeCamp launches free 2-hour course on agentic coding with Codex — adnan_hashmi · 2026-11-12
- A criminally underrated resource comparing tool-calling reliability across models and providers — ricklamers · 2026-11-12
- Organizing 55k data points is easy: enterprise data prep for agents is the hard part — BenBajarin · 2026-11-12