A guide to AI prompting from a blindness perspective
This article was originally written for the Google Developer blog. However, it's been a number of months since I've heard from them, so I'm publishing it here.
@tomayac No worries! Do you need me to take mine down? I just wanted to get it out somewhere before the advice became outdated. I haven't fully tested them, but I think the new gemma defusion models might be better than the Llama-3.2-90B-Vision I'm currently recommending. Unfortunately none of my toolchains support it, so I'm just waiting for some updates to happen. But when they do, it's likely at least one part of that article will already be out of date.
