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)

https://ift.tt/GvEaw8D

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/jW6uZQv