a walkthrough of how LLMs work

“[People] simply drop it into where it needs to go (or not), and somehow, magically, it seems to work. And I am not talking about not remembering flags for Linux cli tooling (tar, looking at you), I am talking about people copy pasting entire piped xargs commands into their terminal and then praying that it doesn’t ruin your day somehow. No thinking, no learning, just slop everywhere. Yes, people did this before AI using Stackoverflow snippets, but at least you had to fit the puzzle piece into your architecture, and think about the code in some way or form. Not anymore.”

An account of using AI to do a project that was just a bit out of reach previously. There’s some really good insights, like comparing AI coding to slot machines.

Quick, interesting read about AI, capitalist consumption and escapsism

LiveKit develops an End-to-end stack for WebRTC. It also added AI agents. They share technical details in their blog.

Blog posts with images get 2.3x more engagement. Here’s the problem - we make a query engine for streaming tables. How the heck are you supposed to pick images for technical topics like comparing the similarities between Deephaven and Materalize, viewing pandas DataFrames, gRPC tooling for getting data streams to the browser, using Kafka with Parquet for storage, or using Redpanda for streaming analytics?

Articles about Machine Learning