Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
visarga
on March 5, 2025
|
parent
|
context
|
favorite
| on:
ARC-AGI without pretraining
Compression works on finite data, and AI models need to keep open for new data. So they should be less greedy.
Consider applying for YC's Summer 2026 batch! Applications are open till May 4
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: