Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
YetAnotherNick
44 days ago
|
parent
|
context
|
favorite
| on:
When AI Benchmarks Plateau: A Systematic Study of ...
So commonsenseqa is the least saturated benchmark? It's like authors don't even read what they publish.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
