Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
artdigital
11 months ago
|
parent
|
context
|
favorite
| on:
GPT-OSS Reinforcement Learning
Mind explaining?
BoorishBears
11 months ago
|
next
[–]
If you constrain the model to a JSON schema, most frivolous refusals go away.
And if you finetune on a few formatted examples the effect is even greater
7thpower
11 months ago
|
prev
[–]
Curious as well
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
