Show HN: Screenshot 2 Text GPT (with vision not OCR)

[gordbegli]

https://chat.openai.com/g/g-fQA8D4yzO-screenshot-2-text

GPT4V tends to rely on OCR instead of Vision to extract text. I found this to be less accurate.

This is basically a prompt that forces vision's use for text extraction.

[Oras]

I just tested it, and it is pretty good. I used an image that ChatGPT struggled to identify twice due to the amount of information but your prompt identified the data correctly and in JSON format.