Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
chippiewill
on Feb 28, 2025
|
parent
|
context
|
favorite
| on:
GPT-4.5
They have examples in the announcement post. It does a better job of understanding intent in the question which helps it give an informal rather than essay style response where appropriate.
j_maffe
on Feb 28, 2025
[–]
I wouldn't call that "too insane." As others have pointed out, you can get similar results from fine-tuning the RLHF.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: