AnthropicAI· @AnthropicAI · X·· 4 天前AI 评分
Anthropic 与 Theorem Labs 用 Claude 大规模验证开源软件安全属性
Anthropic 与 Theorem Labs 合作，使用 Claude 在数周内为超过 100 个真实世界开源库证明安全属性。Anthropic 表示，传统形式化验证过去主要适用于小型代码库或需要大量专家时间，AI 模型正在改变这一限制。研究全文发布于 anthropic.com/research/forma…。
New on our Frontier Red Team blog: using Claude to formally verify software at large scale.
Formal verification can prove that code is free of certain bugs, but historically it has only been feasible for small codebases (or required a lot of expert time).
With AI models, however, this is beginning to change. In collaboration with @theoremlabs, we used Claude to prove security properties in over one hundred real-world open-source libraries over the span of a few weeks.
Read our research in full here: anthropic.com/research/forma…
来源：AnthropicAI · x.com