LLM evaluation
3 published articles
Benchmarks & Tests3 min read
Agent evaluation
Sandbox benchmarks are hiding how agents really fail, HKU just built the fix
UniClawBench evaluates proactive agents across five fundamental capabilities in 400 bilingual real-world tasks, using live Docker containers and a three-agent closed-loop evaluation. It disentangles base model abilities from framework choices, revealing where agents truly break.
2026-07-13
Tools & Frameworks5 min read
Tooling
Your AI model is a commodity. The pipeline is where the real advantage lives.
A practical, step-by-step analysis of building an AI writing pipeline in 2025: model selection, prompt chaining, and quality control. No hype, just the technical architecture that matters.
2026-07-11
LLMs & Models3 min read
Model Evaluation
Ai2's olmo-eval gives LLM developers a microscope for every checkpoint
Ai2's olmo-eval brings per-question diffs and modular benchmarks to active LLM development, helping researchers tell real progress from statistical noise.
2026-07-06