descriptive claim
A set of model weights can be served efficiently only when thousands of sequences are decoded against those weights at the same time.
Dwarkesh Patel · 8 Predictions for the Era of Continual Learning · 7 Aug 2026
In their words
The transcript segments this claim was taken from
“the point here is that a given set of weights is only served efficiently when thousands of sequences are being decoded against it all at once.”Play from 7:40Report a misattribution
95%how strongly it was put, not whether it is true
90%importance to the conversation
98%confidence the claim was read correctly