descriptive claim
The speaker says performance on current AI post-training benchmarks does not necessarily correspond to user preferences.
Dwarkesh Patel · AI researchers debate how close we are to recursive self-improvement · 11 Sept 2026
In their words
The transcript segments this claim was taken from
“And as you were pointing out, the inner loop, even in current AI research of like post training benchmarks or whatever doesn't necessarily translate into what users like.”Play from 9:32Report a misattribution
85%how strongly it was put, not whether it is true
80%importance to the conversation
92%confidence the claim was read correctly