English(EN) Anthropic's Claude now writes code and proves it safe automatically

Anthropic 的 Claude AI 生成代码证明，发现隐藏的错误

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-23 11:32

Anthropic 的 Claude AI 已展示出自动生成数学证明的能力，以验证现有代码的正确性。该过程为 123 个开源库创建了约 1.8 亿行证明代码。值得注意的是，Claude 发现了多年来传统测试未能发现的错误，这表明在 AI 辅助形式化验证方面取得了重大进展。 AI

影响这项能力可以显著提高软件的可靠性，并加速形式化验证方法在开发中的应用。

排序理由该条目描述了一个研究里程碑，其中一个 AI 模型展示了代码验证的新能力。 [lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该条目描述了一个研究里程碑，其中一个 AI 模型展示了代码验证的新能力。 [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: product, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

The Decoder TIER_1 English(EN) · Matthias Bastian · 2026-10-23 11:32

Anthropic's Claude now writes code and proves it safe automatically

<p><img alt="" class="attachment-full size-full wp-post-image" height="768" src="https://the-decoder.com/wp-content/uploads/2026/10/anthropic_claude-2.png" style="height: auto; margin-bottom: 10px;" width="1376" /></p> <p> Anthropic had Claude generate mathematical proofs that ex…