Products & Apps

Anthropic open-sources AI safety audit tool Petri to automatically test model alignment behavior with agents

Original title:Petri: An open-source auditing tool to accelerate AI safety research

AI summary

Anthropic released Petri (Parallel Exploration Tool for Risky Interactions), an open-source automated audit framework that uses AI audit agents to test target models in multi-turn scenarios; the tool is at github.com/safety-research/petri.

Key Takeaways

  • Anthropic released Petri (Parallel Exploration Tool for Risky Interactions),an open-source…
  • the tool is at github.
  • com/safety-research/petri.

Quick Facts

Published
Updated
Source
Anthropic:Alignment Science Blog(网页)
Category
Products & Apps
AI score
71
Read the original Read the full article at the original source
Why it matters

Anthropic 开源了用 AI 智能体自动审计目标模型行为的 Petri 框架,读者可以直接复用其审计流程和评分维度设计。

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: Anthropic open-sources AI safety audit tool Petri to automatically test model alignment behavior with agents. October 7, 2025. https://new.nat6.net/en/news/hx673sxz7gq2e6uvq7rep6u4r/

View all →