https://gnosyslambda.github.io/tags/ai-%EB%B2%A4%EC%B9%98%EB%A7%88%ED%81%AC-%EC%A1%B0%EC%9E%91/ Recent content in AI-벤치마크-조작 on gnosyslambda's log https://gnosyslambda.github.io/images/og-image.png https://gnosyslambda.github.io/images/og-image.png Hugo ko Sun, 19 Jul 2026 00:25:58 +0900 https://gnosyslambda.github.io/posts/2026-07-19-ai-benchmark-model-verification/ Sun, 19 Jul 2026 00:25:58 +0900 https://gnosyslambda.github.io/posts/2026-07-19-ai-benchmark-model-verification/ Basalt Labs의 HLE 99.44% 주장과 서비스 모델 불일치 의혹을 통해 AI 벤치마크, 모델 라우팅, 재현성 검증 기준을 짚습니다.