Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
blackmesaind
on July 10, 2024
|
parent
|
context
|
favorite
| on:
Vision language models are blind
My thoughts as well. I too would have trouble with the overlapping lines tests if all the images underwent convolution.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
