Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
a3w
9 months ago
|
parent
|
context
|
favorite
| on:
Tracing the thoughts of a large language model
Article and papers looks good. Video seems misleading, since I can use optimization pressure and local minima to explain the model behaviour. No "thinking" required, which the video claims is proven.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: