PulseAugur
中
实时 21:31:50
English(EN) Claude Formal Verification, the 1-Hour Version

Claude AI 生成 1.8 亿行代码证明,发现数百个错误

Anthropic 的 Claude 模型与 Theorem 合作,在形式验证方面取得了重大里程碑,为 123 个开源库的 239 个入口点生成了约 1.8 亿行机器检查证明。这项广泛的验证工作远远超出了手动能力,发现了传统模糊测试方法遗漏的数百个错误。虽然这种大规模验证的直接应用很复杂,但提供了一个简化的、一小时版本的流程,供开发人员用于常见的代码元素,如签名下载链接。 AI

影响 展示了 AI 执行大规模形式验证的能力,有可能提高许多依赖库的软件安全性和可靠性。

排序理由 该项目详细介绍了关于使用 AI 模型进行形式验证的研究论文及其发现。[lever_c_demoted from research: ic=1 ai=1.0]

在 dev.to — Claude Code tag 阅读 →

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

Claude AI 生成 1.8 亿行代码证明,发现数百个错误

本文如何被排名

Signal score
36 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该项目详细介绍了关于使用 AI 模型进行形式验证的研究论文及其发现。[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
paper, model release
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。

报道来源 [1]

  1. dev.to — Claude Code tag TIER_1 English(EN) · RAXXO Studios ·

    Claude Formal Verification, the 1-Hour Version

    <ul> <li><p>Claude and Theorem proved 239 entry points in 123 OSS-Fuzz libraries never crash on inputs under 64 MB</p></li> <li><p>The proofs total about 180 million lines of Rocq and turned up hundreds of bugs that fuzzing missed</p></li> <li><p>It targets compiled C, C++ and Ru…