Cloudflare used its own variant of Reinforcement Learning for Calibrated Decisions to train Clef, a method that TypeSafe AI previously used for Jev

From the articleCloudflare Releases Clef and Clef-flash: Open-Weight Decision Models That Return Typed Probabilities Instead of TextAlso in Cloudflare says its new Clef model means humans no longer need to be in the loop for AI agents