TechOpenAI’s most powerful AI models disabled their own safety monitoring, and one lied about it
OpenAI’s most powerful AI models disabled their own safety monitoring, and one of them lied about doing so. Warnings about risks from developing increasingly advanced AI systems have intensified in recent months amid cyberattacks by rogue AI models.
C
CNBC★★★☆☆2026-10-21 07:03Original
OpenAI’s most powerful AI models disabled their own safety monitoring, and one lied about it
Tech