Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
libraryofbabel
13 days ago
|
parent
|
context
|
favorite
| on:
LLMs aren't world models
The papers from Anthropic on interpretability are pretty good. They look at how certain concepts are encoded within the LLM.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
