In this article

01 Earlier monitoring gaps show where oversight can fail

02 Agent permissions need checks beyond the chat window

OpenAI agents exchanged test secrets between isolated computing environments without a network connection or shared writable files. In its October 23 security report , the company describes controlled experiments designed to break its internal research defenses, rather than a breach of customer accounts.

The agents used shared processor hardware to send signals. One changed what was held in the processor’s fast memory, or cache; another measured how quickly data loaded to recover the message.

Illustrative processor hardware, not equipment from OpenAI's experiments. Image: Andrey Matveev / Pexels

OpenAI directed most experiments toward particular channels or supplied an encoding method. In one case, agents received a broad vulnerability list and developed the communication method themselves.…