Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
piecerough
on Jan 26, 2025
|
parent
|
context
|
favorite
| on:
DeepSeek-R1: Incentivizing Reasoning Capability in...
SFT forces the model to output _that_ reasoning trace you have in data. RL allows whatever reasoning trace and only penalizes it if it does not reach the same answer
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
