Do Automated Evals Actually Work?
Hamel Husain · rss · 2026-07-11
The author shared a piece titled Do Automated Evals Work?, which compares 100 human-annotated traces against an automated evaluation system to see if automated assessments are truly reliable.
While the post itself is brief, it clearly defines the research question: using human annotations as a ground truth to test how well automated evals perform on real traces.
More from Research
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11
- VidMap uses RoMa coarse matching on all frames, fine-scale only for keyframes — ducha_aiki · 2026-09-11
- Bug Hunt Bench author: leaderboard noise is about 2-3 points — PawelHuryn · 2026-09-11
- PNAS paper shows a tiny billiard-ball system is a universal computer — undecidability lives in two dimensions — eigensteve · 2026-09-11
- New paper: Absolute pose estimation from affine cues and gravity direction — ducha_aiki · 2026-09-11
- LoMa Paper Ships REALLY HardPairs Dataset, Accepted at ECCV 2026 — ducha_aiki · 2026-09-11