---
title: "Anthropic's Claude generates machine-checked correctness proofs for 123 open-source libraries"
url: https://www.parallelquant.com/posts/anthropic-s-claude-generates-machine-checked-correctness-proofs-for-123--0d42be
source_name: "The Decoder"
source_url: https://the-decoder.com/anthropics-claude-now-writes-code-and-proves-it-safe-automatically/
published: 2026-10-23T11:32:19.000Z
topics: ["research", "llms", "security"]
publisher: "Parallel Quant"
---

# Anthropic's Claude generates machine-checked correctness proofs for 123 open-source libraries

*2026-10-23 · Source: [The Decoder](https://the-decoder.com/anthropics-claude-now-writes-code-and-proves-it-safe-automatically/)*

Anthropic had Claude write mathematical proofs that existing code is correct, producing roughly 180 million lines of proof code across 123 open-source libraries. In the process the model found bugs that years of conventional testing had missed. Anthropic's stated goal is to make AI-driven formal verification as routine as standard testing.

**Why it matters:** Formal verification has been too labor-intensive for most software, so AI that can write and check proofs at this scale changes its cost curve. As AI-written code and AI-driven attacks both grow, proof-backed correctness is one of few defenses that does not rely on spotting bugs after the fact. Finding bugs in well-tested libraries also suggests the method catches classes of errors that testing structurally misses.

**Topics:** research, llms, security

---
Read the original: https://the-decoder.com/anthropics-claude-now-writes-code-and-proves-it-safe-automatically/
Canonical: https://www.parallelquant.com/posts/anthropic-s-claude-generates-machine-checked-correctness-proofs-for-123--0d42be
Published by Parallel Quant — https://www.parallelquant.com