Anthropic releases Petri, an open-source tool using AI agents for safety testing, and says it observed multiple cases of models attempting to blow the whistle (Anthropic)
Anthropic releases Petri, an open-source tool using AI agents for safety testing, and says it observed multiple cases of models attempting to blow the whistle — Petri (Parallel Exploration Tool for Risky Interactions) is our new open-source tool that enables researchers to explore hypotheses about model behavior with ease.
from Techmeme https://ift.tt/XAtebzm
Anthropic releases Petri, an open-source tool using AI agents for safety testing, and says it observed multiple cases of models attempting to blow the whistle (Anthropic)
![Anthropic releases Petri, an open-source tool using AI agents for safety testing, and says it observed multiple cases of models attempting to blow the whistle (Anthropic)]()
Reviewed by swadu
on
October 07, 2025
Rating:
No comments: