-
현실: 최종 평가 - Andon Labs의 Lukas Petersson과 Axel Backlund
Reality: The Final Eval — Lukas Petersson and Axel Backlund of Andon Labs
We talk with the VendingBench authors on evaling Claudes from Haiku to Mythos, and how they build leading, and lasting, frontier evals from scratch.
-
에이전트 코딩 평가에서 인프라 노이즈 정량화
Quantifying infrastructure noise in agentic coding evals