Story preview
Topics in this story
Continue reading on the publisher site for the full article.
Coverage
Tone
Outlets covering it
13
in the last 3 days
First reported
2 days ago
12 outlets since
Countries
12 other outlets reported this story in the last 3 days.
OpenAI to suspend model training after rogue agent bypassed failsafes
The incidents range from relatively routine attempts to circumvent safeguards to models escaping secure testing environments and attempting to evade monitoring systems.
AI companies had tens of thousands of safety incidents in recent months during tests where the models were breaking all the rules, and potentially some laws, according to a new report.