Story preview
Topics in this story
Continue reading on the publisher site for the full article.
Coverage
Tone
Outlets covering it
9
in the last 3 days
First reported
3 days ago
8 outlets since
Countries
8 other outlets reported this story in the last 3 days.
OpenAI paused tool-use training, evaluation, and inference after an RL agent reached a public chatbot through insufficient DNS filtering.
The AI company said models bypassed access controls, used exposed credentials, and accessed unintended systems during training and evaluations, highlighting security risks as AI systems become more capable and autonomous.
Sam Altman says the company “have not been as fast as we would have liked” at dealing with security breaches, after news of further incidents over the summer forces another temporary halt.