On-Policy Distillation: LLM's Post-Training Meta of 2026
Explainer on on-policy distillation, a key 2026 post-training technique for builders tuning smaller models.
More in Models
1:59ModelsGPT-6.2 Astra and GPT-6.2 Sol—Models built for the real world
OpenAIGPT-6.2launch
19:38Models2026 in LLMs — Simon Willison
Simon WillisonAI Engineerkeynote
37:25ModelsHow to compress text to 1 bit per character | Compression is Intelligence Part 3
compressionexplainertutorial





