Diffusion models explained simply(seangoedecke.com)
123 points by onnnon | 25 comments
123 points by onnnon | 25 comments
168 points by tim_sw | 44 comments
804 points by mdp2021 | 215 comments
Simon Willison's blog post on Google's Gemini Diffusion, a diffusion-based LLM announced at Google I/O, noting its speed of about 857 tokens per second.