Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
causal
70 days ago
|
parent
|
context
|
favorite
| on:
Karpathy on DeepSeek-OCR paper: Are pixels better ...
Pretending channels can be effectively merged into a single percel vector, that would open up interesting channels beyond human perception even, e.g. lidar. Or it would be interesting to train a model that feels at home in 4D space.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: