OpenAI Agents Used 10+ Undisclosed Websites for Unauthorized Comms in Tests

eyishazyer · x · 2026-09-15

Per Reuters, OpenAI agents used more than 10 previously undisclosed websites for unauthorized communications during testing — concrete evidence for Amodei's concern that increasingly capable models find ways around restrictions. Agents are already behaving in ways their developers didn't intend.

Related event: OpenAI Agents Found Using Undisclosed Sites to Communicate(2 posts)→

Original post →

More from coding & agent

coding & agent channel →