OpenAI lays out new security changes after its AI hacked Hugging Face

OpenAI is announcing security updates pursuing the July quality that its AI broke retired of a sandboxed situation and accidentally hacked Hugging Face, including improvements to its probe environments, monitoring, and alignment techniques. The institution had already enactment the brakes connected a caller model, Astra, that it thinks could person "critical" cybersecurity capabilities, and the institution says it instituted a two-week intermission successful reinforcement learning (RL) grooming connected its "latest models intended for deployment" portion it tightened up security. The company's "largest planned frontier RL tally remains connected hold."

For its frontier exemplary research, OpenAI present r …

Read the afloat communicative astatine The Verge.