Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
getnormality
5 months ago
|
parent
|
context
|
favorite
| on:
BERT is just a single text diffusion step
You're right that there is long-term planning going on, but that doesn't contradict the fact that an autoregressive LLM
does, in fact, literally
generate words one at a time based on previously spoken words. Planning and action are different things.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: