Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
anon291
on Feb 28, 2025
|
parent
|
context
|
favorite
| on:
Replace OCR with Vision Language Models
That is
one way
of sampling tokens. It is not the only way. Logits do not map neatly to belief, although it is convenient to behave as if they do
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:
