Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
hodapp
10 months ago
|
parent
|
context
|
favorite
| on:
Why LLMs still have problems with OCR
You are right; the advanced in DeepSeek-R1 used RL almost solely because of the chain-of-thought sequences they were generating and training it on.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
