Sarah Chieng(@MilksandMatcha):Pretraining teaches a model to predict. Reinforcement learning teaches it to act. @jeffreygwang of @OpenAI explains how the two paradigms turn next-token prediction into models that can reason, use tools and complete useful tasks. Big Chip Club with @cerebras // @alyciazcary

Sarah Chieng

@MilksandMatcha

Head of DevX @Cerebras prev. @ExaAiLabs, @shopthrifthouse, @MIT wife to @tyler_fong_ 💌 DMs open

Joined March 2022

1.6K Following 27.8K Followers

Sarah Chieng@MilksandMatcha

2026.08.11 20:22

Pretraining teaches a model to predict. Reinforcement learning teaches it to act. @jeffreygwang of @OpenAI explains how the two paradigms turn next-token prediction into models that can reason, use tools and complete useful tasks. Big Chip Club with @cerebras // @alyciazcary