Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
someothherguyy
3 months ago
|
parent
|
context
|
favorite
| on:
Mistral OCR
Wouldn't that just bias itself to the shape of the text extracted from the OCR against the shape of the raw text alone? It doesn't seem like it would be a great benchmark for estimating semantic accuracy?
Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
