A lot of current diffusion LLMs don't convert tokens to continous space before noising them. They add discrete "noise", which is often as simple as replacing some tokens with [MASK].

The real problem is that when using fewer sampling steps than output tokens, diffusion formulations fundamentally cannot represent distributions where output tokens are heavily codependent. Autoregressive formulations don't have this problem, they can represent any distribution (ignoring limitations of the underlying model).