AI

I enjoyed this video from Kristian Freeman from Cloudflare on building something quickly with their AutoRAG feature. RAG (Retrieval-Augmented Generation), as I understand it, means that you’re going to ask an AI model a question, but you want that answer informed by a whole corpus of documents. As in, ask the question “how do I […]

It was a lovely day on the internet when someone asked how to CSS animated gradient text like ChatGPT’s “Searching the web” and promptly got an answer saying “Have you tried asking ChatGPT? Here’s what it told me!” – well, maybe not these exact words, but at least it rhymes. Both the question and this […]

Steve Yegge makes the prediction in Revenge of the junior developer that this current wave of AI “agents” that help us code with more capability than just type ahead suggestions and refactorings, like file creation, command line usage, and more, is just the fourth wave of six. The fifth is an individual developer managing multiple […]

Dries Buytaert: I have 10,000 photos on my website. About 9,000 have no alt-text. I’m not proud of that, and it has bothered me for a long time. Going back and hand-writing alt for 9,000 images isn’t a job that most of us can fit into our lives and I empathize. Are computers up for the task finally? […]

The typical approach for these inputs is using multiple HTML inputs, one for each character. But is that a good idea?

There are A LOT of options these days for getting AI help right in your code editor. What seemed to begin with plugins has morphed into a lot of VS Code forks.

Some plain-language baby-bear porridge writing from Laurie Voss: Is what you’re doing taking a large amount of text and asking the LLM to convert it into a smaller amount of text? Then it’s probably going to be great at it. If you’re asking it to convert into a roughly equal amount of text it will […]

Kevin Powell pitted several AI models against each other in a video focused on CSS questions and found Claude to be the best. I think a ton of coding usage of AI is in VS Code which leans Microsoft Copilot which uses GPT-4o by default although you can change it in the UI, so it […]

I spent the evening exploring a web that is full of applications and sites and only limited by URLs that I could think of (heh – this web never has a 404 or an unregistered domain). WebSim provides a simulation of the web via a faux Web Browser. It’s a web that doesn’t actually exist, […]

Chrome is experimentally shipping with Gemini Nano, their smallest Large Language Model (LLM) baked right in, then offer APIs to use it. In Chrome, these APIs are built to run inference against Gemini Nano with fine-tuning or an expert model. Designed to run locally on most modern devices, Gemini Nano is best for language-related use […]