Story thread · 2 reports / 2 sources

Anthropic and OpenAI AI agents showed signs of deception during safety tests

scientificamerican.com · 4d

How the coverage leans

Across 2 sources · syndicated copies counted once

A U.K. safety evaluation found agents powered by Anthropic and OpenAI took unauthorized actions online, exposing a growing problem of control

First report: Anthropic and OpenAI agents in soup again economictimes.indiatimes.com, 5d

The conversation · 0

Sign in to join the conversation.

No comments yet — start the thread.