Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
ogogmad
on Dec 21, 2024
|
parent
|
context
|
favorite
| on:
OpenAI O3 breakthrough high score on ARC-AGI-PUB
> They can't go beyond the boundaries of their training set.
TFA says they just did. That's what the ARC-AGI benchmark was supposed to test.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
TFA says they just did. That's what the ARC-AGI benchmark was supposed to test.