Skip to contentSkip to filters

We use cookies for analytics.

Post-Training Is Where Models Are Made Now | Maxime Labonne

Related content

About

Maxime Labonne, head of post-training at Liquid AI and author of the LLM Course, traces post-training from supervised fine-tuning and preference optimisation to reinforcement learning with verifiable rewards and multi-domain on-policy distillation, in which separate code, maths and other domain teachers are merged back into one student model. He explains why supervised fine-tuning cannot be skipped, why stage order matters, why reinforcement learning works although a long rollout yields about one bit of signal, and his view that fine-tuning and distillation raise pass@k while reinforcement learning sharpens it into pass@1. The conversation also covers training small agentic models inside their harness, open-source reinforcement-learning stacks, looping transformers, why models now write worse, safety and regulation, open and Chinese models, and whether Europe can build frontier models.

Topics

Details

Show

The Information Bottleneck

60 episodes on World Wide · The Information Bottleneck