Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
int_19h
5 months ago
|
parent
|
context
|
favorite
| on:
GPT-4.1 in the API
I actually agree with that, but it's generally better than other scores. Also, the quote is like a year old at this point.
In practice you have to evaluate the models yourself for any non-trivial task.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
In practice you have to evaluate the models yourself for any non-trivial task.