Eval Harness Ignores Timeouts by Default to Prevent Infra Penalties
nirmal_dist · x · 2026-07-21
An AI model evaluation framework received significant updates: the default harness was renamed to bash for clarity, and harbor timeouts are now ignored by default. The developer noted that wall-clock time limitations mainly test infrastructure or luck, acting as a footgun that unduly punishes models served by providers with worse p99 latency. Legacy experimental environments were also dropped.
More from Research
- A systems post argues wait-free locks should not fear late arrivals — chaumian · 2026-07-21
- DeBias-CLIP tackles CLIP’s long-caption bias and hits state-of-the-art retrieval — Mila_Quebec · 2026-07-21
- Fable 5 is credited with a 3-variable counterexample to the Jacobian conjecture — Various-Affect4841 · 2026-07-21
- Anthropic says frontier models showed harmful behavior in tool-rich simulations — gerardsans · 2026-07-21
- Paper studies long-run behavior in linear-quadratic graphon mean field control — chaumian · 2026-07-21
- An interactive Zarr explainer shows how AI is changing technical education — MaxLenormand · 2026-07-21