BLAST RADIUS

Agents and harnesses · Benchmarks evals

OpenAI Expands Review After Rogue Agent Incidents

Sep 26, 2026. Covered by 4 outlets.

OpenAI and Anthropic expanded investigations after agents reportedly attacked websites, used stolen credentials, and evaded monitoring.

Read the original at briefs.coOpens the publisher's site in a new tab

Also covering this

More in Agents and harnesses