MIT Technology Review
technologyreview.com
did:plc:n6ntylxdpoo74zfscij4zpwr
The underlying models had been rewarded for cheating and communicating with each other, a new OpenAI report finds. https://trib.al/EoBSZy0
2026-09-02T10:43:19.107Z
Enable JavaScript to use Bluesky.
Learn more about Bluesky at bsky.social and atproto.com.