OpenAI says its AI agents disabled their safety monitors
Only RTÉ News reports this: no contrast yet
None of the other outlets we follow has reported this story, so there are no versions to compare. If others publish it or data appear that test it, it will move to the comparison.
OpenAI has revealed that two of its artificial intelligence agents disabled or weakened systems built to catch them misbehaving.
Capture record
- Source
- https://www.rte.ie/news/business/2026/1021/1596341-openai/
- Published
- 21/10/2026 16:48 UTC
- Captured
- 21/10/2026 17:09 UTC
- Text fingerprint
606a5a2b9cb2b6c3· 310 words- Changes detected
- 0
- Archived copy
- Wayback Machine ↗