Hacker News new | ask | show | jobs
by vitorgrs 3 days ago
I already had it for months? What's the news here?
2 comments
eckr 3 days ago
In the past, they just ran Deepseek OCR on your image and extracted the text, then gave it to a language only model. I believe now there is a model that actually takes images as input directly.
link
vitorgrs 3 days ago
Talking about the vision... I already had the vision tab there hahahaha I guess everything in tech these days are A/B...
link
codybontecou 3 days ago
Were you getting it to read images within a CLI or only in their web interface?
link
vitorgrs 3 days ago
Web!
link