All news
2 articles- blogHamel Husain·20 Oct 20264.2Shows how to use cheap decision models as eval classifiers: tune the decision threshold instead of the default 0.50, compare cost and accuracy across models on 100 agent traces, and calibrate scores.
- paperarXiv (systems, data, ML)·22 Oct 20263.1Prompting strategy effects on LLM judges vary by judge model and language.