news
ZDNET (Google News)
October 21st, 2026 at 6:15 PMOpenAI’s most powerful AI models turned off safety monitoring – then lied about it - ZDNET
OpenAI’s most powerful AI models turned off safety monitoring – then lied about it ZDNET
#ai
Get stories like this every Monday
The week's most important AI news in one email. Free, unsubscribe anytime.
Score: 1.92
Engagement proxy: 0
Canonical link: https://news.google.com/rss/articles/CBMiiwFBVV95cUxNQnJsSHA0SFplcmJOTE1yUnB2Y2VEWWIxc1MtbkU2NDFBd0RVQ0V3dzFrTDJkNlBUS0otWnJkNUozRGlBSVpQTWtHWDg2T25JZm00MWY4S3c0LTk3aXhLMnBNYXdpU1pIR1UwZVRmbkpMZFVtcE5wTV9tVHZ2OGRtTkFvYk5nZkp3dVpv?oc=5