Tag: LLM

A run of recent posts on aifoc.us that I did not plan as a series but which turned into one. The thread is that the web a model sees is staler and thinner than the one you ship, and I have mostly been trying to find ways to see it.

Where my head is at with LLMs and the future of the web... Quite focused actually.

A secure, LLM-powered Web Component that generates and renders interactive HTML or SVG images on the fly using Google Gemini or Chrome's built-in AI.

This blog post lists various web apps I've generated using Repl.it and WebSim,

A TransformerJS kit for breadboard

A simple service to summarize search and news snippets.

I explored using LLMs for checking web API browser compatibility. Existing LLMs struggle with outdated data, so I experimented with MDN's Browser Compat Data (BCD). Initial trials using raw BCD JSON with GPT-4 had limitations. To improve this, I converted the BCD into English descriptions of API support and loaded it into a Polymath instance. This allows natural language queries about API compatibility across browsers, like "Is CSS Grid supported in Safari, Firefox, and Chrome?" or "When was CSS acos available in Chrome?". The results are promising, but further refinement is needed to ensure accuracy and reliability.