2 releases covered on ThursdAI · haizelabs.com ↗
Haize Labs releases j1-nano and j1-micro tiny reward models
Haize Labs shipped j1-nano (600M params) and j1-micro (1.7B params), tiny open reward models for judging LLM outputs. Despite their small size, j1-micro scores 80.7% on RewardBench, making capable reward modeling accessible on modest hardware.
Haize Labs open-sources Verdict, a framework for composing LLM judges
Haize Labs released Verdict, an open-source framework for composing LLM judges that tackles core LLM-as-a-judge problems: self-preference bias, prompt sensitivity, and meta-evaluation. Verdict combines simpler judging primitives into more robust and efficient evaluators ('judge-time compute scaling'), achieving near state-of-the-art results on benchmarks like ExpertQA at a fraction of the cost, fast enough to use as a real-time guardrail. Co-founders Leonard Tang and Nimit joined the show to discuss it.
Never miss a Haize Labs launch — we cover every release live, every Thursday.