Re:Mercury Coder: frontier diffusion LLM generating 1000+ to...
by volodia on Wednesday February 26, 2025 @05:44PM
(#43189141)
The short answer is that we do more than one parallel pass over multiple tokens: we iteratively refine them over a few passes to fix incoherences. This can be seen as a generalization of diffusion algorithms that underlie systems like Midjourney or Sora.
[ Parent
| on HN ]