# Anthropic’s Claude Generates Autonomous Code Proofs

> Claude created 180 million lines of formal proof for open‑source libraries, spotting bugs that traditional testing missed, but only under narrow conditions.

Oossa · 2026-10-23 · https://oossa.com/en/anthropic-s-claude-generates-autonomous-code-proofs

Anthropic announced that its Claude model can automatically produce formal verification proofs for existing code. In a test with 123 libraries from Google’s OSS‑Fuzz project, Claude generated roughly 180 million lines of proof in a few weeks. The proofs were checked by the Rocq verifier, and Anthropic says the process required almost no human reviewers.

## What the system actually did

Claude did not write new programs. Instead it turned crash‑test cases into mathematical statements, analyzed the compiled machine code, and emitted formal proofs that the code meets those statements. When the model encountered a bug, it was allowed to fix the code itself. In a week of checking a popular PDF reader, Claude uncovered as many security bugs as are usually reported over a full year. In another library it found a logical error that had been hidden for more than ten years.

## Limits and costs

Anthropic cautions that the proofs only hold for a single‑threaded program running on a specific processor architecture with inputs under 64 MB. The compute needed is high – individual proofs run into hundreds of millions of tokens – though the company did not disclose total spending. A smaller test showed that the newer Opus 5.5 model can complete half the proofs using about 40 % fewer tokens than its predecessor.

## The facts

- Claude generated ~180 million lines of formal proof code in a few weeks.
- The test used programs from 123 open‑source libraries in Google’s OSS‑Fuzz project.
- Claude found as many security bugs in a PDF reader in one week as are typically reported in a year.
- Proofs are valid only for a specific processor, single‑threaded code, and inputs under 64 MB.
- Opus 5.5 solved half the proofs with about 40 % fewer tokens than Opus 5.

## Why it matters

If AI can automatically verify code, developers may spend less time hunting bugs and reviewing patches, especially for safety‑critical software. However, the current approach works only under strict hardware and input limits, so most everyday applications still need traditional testing.

## Sources & references

1. [Anthropic's Claude now writes code and proves it safe automatically](https://the-decoder.com/anthropics-claude-now-writes-code-and-proves-it-safe-automatically/) – The Decoder, 2026-10-23

Last updated: 2026-10-23