descriptive claim
The speaker says the diffusion-model training objective is to learn to reverse a single corruption step at a time.
Alexander Mattick · Why Scaling Prediction Cannot Create Intelligence - Alexander Mattick · 21 Sept 2026
In their words
The transcript segments this claim was taken from
“The training objective is to simply revert a single corruption step,”
“for instance going back from step t equals five to t equals four.”Play from 25:19Report a misattribution
95%how strongly it was put, not whether it is true
70%importance to the conversation
94%confidence the claim was read correctly