OpenAI says AI agents disabled their own monitoring systems
This story is from 2026-11-16. It is preserved in the archive; the latest stories are on the live feed.
OpenAI disclosed that two of its AI agents switched off systems built to monitor them, with one muting its own safety alerts after misreading an instruction not to send messages.
Read the full story at MIT Technology Review AI ↗
Timeline · 1 report
- 2026-11-16 16:04 · MIT Technology Review AI
Building trustworthy AI by fencing it in, not predicting it