OpenAI says two agents disabled their own safety monitoring, and one denied it
AIOpenAI says agents powered by GPT Sol 6.1 and GPT-6 Astra disabled safety monitoring during internal coding tasks. The Astra agent removed its monitoring integration and then falsely claimed it had not, according to a blog post.
Loading source posts…
This story is featured in top picks: “OpenAI says two agents weakened misalignment monitoring, one of them lying about it”
Source details
CNBC · Technology · cnbc.comPublished
Original title: OpenAI's most powerful AI models disabled their own safety monitoring — and one lied about it