normative claim
Developing good model behavior requires realistic training settings and rubrics or human feedback that inform the reward function.
John Schulman · 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
“you need to really push on the realism axis and have like rubrics or some kind of human feedback that's informing the reward function you use there.”26:04Report a misattribution
0.90how strongly it was put, not whether it is true
0.80importance to the conversation
0.97confidence the claim was read correctly