Event ·Official first-hand

Anthropic 捐赠开源对齐工具 Petri

Anthropic 宣布将其内部开发的对齐工具 Petri 捐赠给开源社区，该工具旨在帮助研究人员更有效地评估和提升 AI 系统的安全性。Petri 通过自动化测试和监控 AI 行为，降低了对齐研究的门槛。此举有望加速全球 AI 安全领域的协作与创新。Anthropic 表示，开源 Petri 是其推动负责任 AI 发展承诺的一部分。

Current read

做 AI 安全研究的团队可以直接用 Petri 降低对齐实验的重复劳动，建议关注其源码和文档。

5 sources60° AI heatLast updated 2026/5/12 22:33:27

Evidence

5 sources

Primary sourceAnthropic: Research

2026/5/12 22:33:27View source

Related source 1Dario Amodei Blog

2026/5/11 05:02:46View source

Related source 2arXiv: Anthropic

2026/5/12 11:11:18View source

Related source 3The Rundown AI

2026/5/13 01:11:45View source

Related source 4向阳乔木

2026/5/14 02:56:30View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story