Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
billythemaniam
on March 21, 2023
|
parent
|
context
|
favorite
| on:
GPT-4 and professional benchmarks: the wrong answe...
So far GPT-4 seems to improve on this problem. Still happens but less frequent.
mtlmtlmtlmtl
on March 21, 2023
[–]
I'm assuming you base this on hard empirical data and not just that it feels like it when you use it? ;)
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: