opinion claim
The speaker says supervised fine-tuning and on-policy distillation can damage a model excessively.
Unresolved speaker · AI researchers debate how close we are to recursive self-improvement · 11 Sep 2026
In their words
The transcript segments this claim was taken from
“A little bit of both. I think like SFT and even like just like on policy distillation can be like way too destructive.”56:29Report a misattribution
0.85how strongly it was put, not whether it is true
0.75importance to the conversation
0.92confidence the claim was read correctly