News for hackers. Stuff that matters.
Re:The killer app of Gemini Pro 1.5 is video by llm_nerd on Thursday February 22, 2024 @09:55AM (#39467985)
You understand that OCR is the process of extracting text from images, right? You know, such as what Gemini does, and they reference repeatedly in their paper. I have absolutely no idea why you repeatedly make some bizarre distinction about it being a "separate process".

Okay, it's been fun talking to you but feel free to have the last word. Good luck.

Re:The killer app of Gemini Pro 1.5 is video by og_kalu on Thursday February 22, 2024 @10:02AM (#39468095)
The transformer (Gemini) predicts text with image and text in the context window. That's it.

OCR, Object detection etc all come from the transformer predicting text. Read the Flamingo paper.