definition claim
On-policy self-distillation trains a base model to match the predictions of a context-enriched model after a long session.
Dwarkesh Patel · The next big breakthrough will be AIs learning on the job · 26 Jun 2026
In their words
The transcript segments this claim was taken from
“But to summarize the explanation,”
“the idea is that we encourage the base model to make the same predictions when trying to solve some real-world problem.”
“as the model with all the context accumulated after a long session would have made.”Play from 13:09Report a misattribution
95%how strongly it was put, not whether it is true
90%importance to the conversation
99%confidence the claim was read correctly