descriptive claim
Diffusion-based language models can remain transformer-based and use attention, allowing them to benefit from existing architectural work.
Stefano Ermon · Why Diffusion Will Win AI Inference with Inception Co-Founder and CEO Stefano Ermon · 18 Sept 2026
In their words
The transcript segments this claim was taken from
“it's still a transformer-based model,”
“so you don't have to throw away a lot of the work that has been done on good architectures.”
“We still use attention.”Play from 14:37Report a misattribution
95%how strongly it was put, not whether it is true
80%importance to the conversation
95%confidence the claim was read correctly