# Anthropic Uses Claude to Verify 123 Open Source Libraries

> Anthropic used Claude to formally verify 123 open-source libraries, finding defects missed by standard testing and review.

- Type: AI news
- Page: https://completeaitraining.com/news/anthropic-uses-claude-to-verify-123-open-source-libraries/
- Published: 2026-10-23
- Updated: 2026-10-23
- Author: Jeroen Erne
- Jobs: Education, Healthcare, Human resources, IT and development, Legal, Management, Science and research, Writers
- Reading time: 1 min

Anthropic applied its Claude model to formally verify security properties in 123 open-source software libraries. The process identified defects that had remained undetected through standard testing and review practices.

Formal verification at this scale represents a notable step for software assurance, offering a method to mathematically prove that code behaves as intended. The findings suggest that automated reasoning tools can surface vulnerabilities that manual audits and conventional static analysis might miss across large codebases.

Independent reproduction of the results remains essential to confirm the reliability of the approach before it can be considered a standard practice in development, security, or compliance workflows.

---

This is the Markdown form of https://completeaitraining.com/news/anthropic-uses-claude-to-verify-123-open-source-libraries/. The whole site is mapped at https://completeaitraining.com/llms.txt.