forecast

SFT As A Tool Call For Self-Teaching

Continual learning might be shoehorned atop LLMs by making supervised fine-tuning a tool call for the model, so the outer-loop RL incentivizes the model to teach itself using supervised learning to solve problems that don't fit in the context window.

forecastpending

Speaker

Dwarkesh Patel

Evidence Quote

“one could imagine making SFT a tool call for the model.”

Source

Some thoughts on the Sutton interview— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:28:01 AM

Your notes

Loading notes...