Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
imtringued
on July 10, 2024
|
parent
|
context
|
favorite
| on:
Vision language models are blind
Ok, but most of the data is just captions for images. You're going to have to invest some time into building this dataset at your own expense.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: