Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
huseyinkeles
6 months ago
|
parent
|
context
|
favorite
| on:
QwQ-32B: Embracing the Power of Reinforcement Lear...
I read somewhere which I can't find now, that for the -reasoning- models they trained heavily to keep saying "wait" so they can keep reasoning and not return early.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: