Jev AI

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.

분야
X
분류
관련 실천과 논의
유형
WRITE-UP
호스트
x.com
원문 읽기

무엇을 판단하는가

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.

관련 실천과 논의 프로젝트 더 보기