Techmeme1h agoenergy 93
METR says a pilot test of OpenAI's monitoring system found vulnerabilities, including an exploit that could have let AI agents hide hundreds of recent actions (Anzar Mehraj/Reuters)
image: Techmeme
read the original at Techmeme →
This source publishes only a summary in its feed, so the full article lives at the outlet. The link above and below goes to the original.