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
- Nature paper images cellular activity across all organs, revealing body-wide circuits — arjunrajlab · 2026-09-11
- SignNet 1M Dataset Released for Sign Language Research — ducha_aiki · 2026-09-11
- ECCV26 Oral: Flow Matching Enables Single-Stage Multi-View Point Cloud Registration — ducha_aiki · 2026-09-11
- InFlux++ Method Released — ducha_aiki · 2026-09-11
- Skyfall GS Uses Flux to Refine Gaussian Splatting, Accepted at ECCV 2026 — ducha_aiki · 2026-09-11
- Could 10k agents discover learning methods beyond backprop, or just tweak existing ones? — SeunghyunSEO7 · 2026-09-11