Anthropic 让 Claude 自动为代码生成形式化安全证明
原标题：Anthropic's Claude now writes code and proves it safe automatically
AI 摘要
Anthropic 的前沿红队与 Theorem 合作，让 Claude 对 123 个开源库的现有代码进行形式化验证，在数周内生成了约 1.8 亿行数学证明代码，并发现数百个常规测试遗漏的 bug。Claude 还能自行修复部分问题，证明由 Rocq 独立校验，几乎无需人工审查。Anthropic 承认该方法存在严格限制（特定架构、单线程、输入小于 64MB），且算力成本高昂，但认为 AI 形式化验证有望像常规测试一样普及。
正文节选
Anthropic's Claude now writes code and proves it safe automatically Key Points - Anthropic and partner Theorem used Claude to mathematically verify existing software code and generate formal proofs of its correctness. - The model produced roughly 180 million lines of proof code for 123 open-source libraries in just a few weeks. Along the way, Claude caught hundreds of bugs that conventional testing had missed. - If AI can write code and prove it's correct, software automation might take a major