Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
jprete
12 months ago
|
parent
|
context
|
favorite
| on:
30% drop in O1-preview accuracy when Putnam proble...
Any problem set that can make news is implicitly an LLM benchmark.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
