descriptive claim
Post-training can be mishandled in ways that are not detected by benchmarks.
John Schulman · 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
“Like, so it's like really easy to screw up post-training in some way that doesn't show up in benchmarks.”Play from 27:39Report a misattribution
90%how strongly it was put, not whether it is true
75%importance to the conversation
96%confidence the claim was read correctly