alright, i have to declare this as a strong opinion — #LLMs are better at alt-text than people are
the goal of alt text is to let a person “without eyes” see the picture, to get the same experience as someone who can see fine
but often, almost always, human-written alt text is either too succinct to be helpful, or just an extension of the post itself, and so doesn’t help an impaired person understand what’s in it
OTOH #LLMs generate what “the average person sees”. that stochastic parrot behavior is actually quite desirable, it gives impaired people as close to the same experience as non-impaired
i’m at the point where i don’t even edit the LLM-generated text, because, if it wasn’t clear to the AI, maybe it’s not clear to most people either
the one big problem is that i don’t give the LLM context when i ask for alt text, so its interpretation is worse than a typical human would be. That’s easy to solve, ofc, just paste the post into the prompt. But it takes time and i get lazy. I wish mastodon clients automated this process better
it took a long time to get to this point. One issue i had is that humans are clearly smarter than these LLMs. But after thinking about it, i’m not sure that’s a good thing, typically a dumb but detailed description is a lot more vivid and helpful to someone who can’t see well
Add comment