4 sources healthy · latest episode 9 Nov 2026
descriptive claim

Alexander Mattick says diffusion models involve KL-divergence minimization in a Wasserstein space.

Alexander Mattick · Why Scaling Prediction Cannot Create Intelligence - Alexander Mattick · 21 Sep 2026

In their words

The transcript segments this claim was taken from

“How you would expect the information to to proceed through these models. Especially in diffusion, I could say with these diffusion models. In diffusion models we have this uh the structure that they are doing uh how how was it called? That they they are doing K_L divergence minimisation in a Wasserstein space.”
1:07:01Report a misattribution
0.80how strongly it was put, not whether it is true
0.70importance to the conversation
0.90confidence the claim was read correctly