Jev as an AI agent safety monitor
test report using Jev to check each agent action first, reportedly catching most attacks with almost no false blocks and much lower latency.
何を判断するか
CHOICE
Picks one option from a fixed set
SCORE
Rates against ordered levels
NOUL
Answers a yes / no question
Inferred from this project's own one-line summary in the community list — it reads as a NOUL decision. Read the source to confirm.
関連する実践と議論の他のプロジェクト
Introducing System One Models and Jev (Hacker News)1,800-point launch thread whose ~480 comments debate whether typed decisions replace LLM calls for classification, routing, and verification.Launch thread by Diogo Almeidathe 63k-like announcement from TypeSafe's founder arguing RLCD-trained decision models are a shorter path to economic value than chat models.Model router built with Jev948-like demo where Jev decides which model should serve a request before it is forwarded.MLP on Qwen 4B mimicking Jevbuilder reports that a small MLP trained on top of Qwen 4B already reproduces Jev-like decision behaviour.