Attached: 1 image
Results from tracking 26,309 images accross 1,627 instances.
Then filtering down to the top 1000 instances by active user from instances.social who hhad posted atleast 32 images (2x the average).
They’re doing really well! Do you think Lemmy should also implement alt text?
Writing good alt text is more than just identifying the objects in an image. It requires some understanding of the context around why the image is being included. Harvard provides some great advice for humans to do this well at https://accessibility.huit.harvard.edu/describe-content-images.
Unless Elon puts Tesla’s FSD team on this problem, it will be many years before AI can do this well. With the FSD team on it, it would only take a decade.
There already is alt text in the markdon in the body, but yeah it would be good to have it for the header picture too.
Although I’m hoping for AI to be able to do that automatically.
Writing good alt text is more than just identifying the objects in an image. It requires some understanding of the context around why the image is being included. Harvard provides some great advice for humans to do this well at https://accessibility.huit.harvard.edu/describe-content-images.
Unless Elon puts Tesla’s FSD team on this problem, it will be many years before AI can do this well. With the FSD team on it, it would only take a decade.