Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
visarga
on Dec 3, 2023
|
parent
|
context
|
favorite
| on:
LLM Visualization
The deeper you go, the higher the order. It's what attention does at each layer, makes information circulate.
tsunamifury
on Dec 3, 2023
[–]
Thanks, I assumed that was the case, but they didn't make that explicit. Then the question is, is the world simulation running at the highest order attention layer or is it an emergent property of the interaction cycle between the attention layers.
Consider applying for YC's Spring batch! Applications are open till Feb 11.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
