foreman-jev-evaluation
MahdiHedhli/foreman-jev-evaluation
JEV evaluation (FM-JEV-01): replay-only, advisory-only evaluation of Foreman-style supervision with TypeSafe Jev. Measures how much safety comes from the model versus a deterministic evidence gate. No worker authority.
研究と評価Python
- スター
- 0
- フォーク
- 0
審査時の参照元
参照元を見るトピック
jevagent-supervisionai-safetyevaluation-harnessllm-evaluationtypesafepython