descriptive claim
The speaker says that the year after the GSM-AK capability, models could solve math benchmark problems that might take an expert human mathematician about one minute.
Unidentified speaker · Noam Brown – Agent swarms, alignment, & recursive self-improvement · 17 Sept 2026
In their words
The transcript segments this claim was taken from
“Then the next year they were able to do the math benchmark problems and these would take a human math with like an expert human mathematician maybe like a minute to do and then you get to Amy.”Play from 24:47Report a misattribution
90%how strongly it was put, not whether it is true
55%importance to the conversation
91%confidence the claim was read correctly