Async RL Training at Scale

Inference-time scaling for LLMs-as-a-judge.

Skill to annotate and create ai judges from agent logs

j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.

a single interface around speech-to-speech foundation models

nyc is so back

⚖️ Awesome LLM Judges ⚖️

A subset of jailbreaks automatically discovered by the Haize Labs haizing suite.

Red-Teaming Language Models with DSPy

Sphynx Hallucination Induction