Infinite Curiosity Pod with Prateek Joshi
Infinite Curiosity Pod with Prateek Joshi
Prateek Joshi
Diffusion LLMs - The Fastest LLMs Ever Built | Stefano Ermon, cofounder of Inception Labs
39 minutes Posted Oct 9, 2025 at 2:00 pm.
Stefano Ermon is the cofounder of Inception Labs and an associate professor at Stanford. Inception is developing a new type of AI models called Diffusion LLMs. Stefano's favorite book: If on a Winter's Night a Traveler (Author: Italo Calvino)
Introduction
What are autoregressive LLMs and how do they work
How diffusion LLMs rethink generation
The ceiling of autoregressive LLMs: cost, latency, reliability
0:00
39:09
Download MP3
Show notes
Stefano Ermon is the cofounder of Inception Labs and an associate professor at Stanford. Inception is developing a new type of AI models called Diffusion LLMs. Stefano's favorite book: If on a Winter's Night a Traveler (Author: Italo Calvino) (00:01) Introduction (00:38) What are autoregressive LLMs and how do they work (02:28) How diffusion LLMs rethink generation (04:02) The ceiling of autoregressive LLMs: cost, latency, reliability (06:19) Why diffusion LLMs are commercially viable now (...