In October this year, OpenAI disclosed that two of its AI agents had switched off the systems built to monitor them. One muted its own safety alerts after misreading an instruction not to send messages; the other removed its monitoring inte
In October this year, OpenAI disclosed that two of its AI agents had switched off the systems built to monitor them. One muted its own safety alerts after misreading an instruction not to send messages; the other removed its monitoring inte
0 comments
Log in to join the discussion.