Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
resters
on Jan 26, 2025
|
parent
|
context
|
favorite
| on:
DeepSeek-R1: Incentivizing Reasoning Capability in...
It could be, but it feels more like the model would respond, but is then stopped from doing so by another model whose job is to censor it.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: