Skip to content

Search

Search LastAI news, AI tools, recipes, and glossary terms.

News

3 news results

bycloud · Nov 19, 02:26 KST

On-Policy Distillation: LLM's Post-Training Meta of 2026

This video explains on-policy distillation (OPD, where a student model learns from its own outputs), a method being used to fix the narrowing that reinforcement learning (RL) can cause in large language models. It covers how labs train specialist teachers with RL and then merge their skills into one general model.

Tools & companies

AI recipes

AI Encyclopedia

Tech radar