Post

Chrome shipped an LLM Prompt API to the web platform. At Mozilla, we oppose this API. Here's why:

I'm very grateful for people pushing back. I used the API, have some strong ideas how to make great things with it, but the legal aspects of it are broken as-is

I'm interested in this for generating alt text on edge devices. And model being different device to device and over time is a nightmare and a half. I am p annoyed that they released this with gemini nano 3 (instead of waiting for the gemma4-based gemini nano 4), it's a waste of space rn.

I gave a talk on this with inspirational but overall useless demos. The idea was that the model would solve problems by generating code and the prompt was not tailored much beyond telling it that. The code would then run sandboxes in the page and be endowed with references necessary to do things.

A user could say "I want this bulk action, create a button that'll do it for me" and get the AI to use APIs exposed by the UI to implement a custom feature no startup of company would want to put permanently in their product.

I would not have to adjust the prompt, bit I'd even prefer for an API for code generation to already exist, so the browser could decide to customize the system prompt of the model it ships with. The prompt optimizations could be partially solved by there being an "extensions store" but for prompts