Hacker News new | ask | show | jobs
by agnishom 414 days ago
I'd hope that with diffusion, it would be able to go back and forth between parts of the output to adjust issues with part of the output which it had previously generated. This would not be possible with a purely sequential model.

However,

> Prompt: Write a sentence with ten words which has exactly as many r’s in the first five words as in the last five

>

> Response: Rapidly running, rats rush, racing, racing.

1 comments

Why not possible with autoregressive model?

o4 mini

https://chatgpt.com/share/681315c2-aa90-800d-b02d-c3ba653281...

Thanks! I didn't know o4 was autoregressive!