Firefox 130 is bringing a game-changing feature: automatic alt-text generation for images using a fully private on-device AI model! 🙌🏾
Initially available in the built-in PDF editor, our aim is to extend this to general browsing for screen reader users. https://hacks.mozilla.org/2024/05/experimenting-with-local-alt-text-generation-in-firefox-nightly/
Trusting this as a blind person would be a terrible idea, unless you had someone nearby who could verify the LLMs output (at which point they could just describe the image to you). At least it’s local.
Trusting this as a blind person would be a terrible idea, unless you had someone nearby who could verify the LLMs output (at which point they could just describe the image to you). At least it’s local.