Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
Legend2440
4 months ago
|
parent
|
context
|
favorite
| on:
Karpathy on DeepSeek-OCR paper: Are pixels better ...
Neural networks have essentially solved perception. It doesn't matter what format your data comes in, as long as you have enough of it to learn the patterns.
Sharlin
4 months ago
[–]
The information density of a bitmap representation of text is just silly low compared to normal textual encodings, even compressed.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: