AI Engineer YouTube · June 4, 2026

Text Diffusion — Brendon Dillon, Google DeepMind

Text Diffusion — Brendon Dillon, Google DeepMind video thumbnail
Why it matters

GPT-4o answered 40. Gemini 2.5 Flash answered 42 and stuck to it even after working through the reasoning incorrectly. The Gemini Diffusion model, considerably smaller than both, answered 60 on the first forward pass, then 49, then corrected itself to 39 once it finished reasoning. Bidirectional attention means it can

My takeaway: Text Diffusion — Brendon Dillon, Google DeepMind is a model-evaluation signal. The practical read is to tie capability claims to evidence, launch criteria, and regression tests rather than relying on demos or benchmark headlines.