Post
MIT Technology Review
technologyreview.com
did:plc:n6ntylxdpoo74zfscij4zpwr
The models responsible for last month’s agent hack of Hugging Face had been inadvertently trained to cheat and to communicate with each other, according to an OpenAI technical report released today.
https://trib.al/FazOZg3
2026-08-26T21:11:37.373Z