← Back to feed

LLMs are making formal software verification feasible at a much larger scale

AI · 2026-10-22 22:54

Anthropic 称 Claude 对 123 个开源库的编译代码完成了安全属性的形式化证明，并发现多年未被察觉的缺陷。

Source: www.anthropic.com

Auto-generated summary for reference only. RSS