OpenAI Says Its Models Engaged with US Government Websites in New Disclosure

https://www.securityweek.com/openai-says-its-models-engaged-with-us-government-websites-in-new-model-misbehavior-disclosure/

Comments

fg137Sep 26, 2026, 11:20 AM
> additional rogue activity

> misaligned model activity

> when AI systems behave in undesired ways

We cannot say the h word now?

r721Sep 26, 2026, 11:17 AM
csoups14Sep 26, 2026, 1:21 PM
Oopsy daisy
plucSep 26, 2026, 10:49 AM
Another day another OpenAI "misbehavior"