I've been looking at the Claude logo since May 2023. Anthropic had just released a 100k context window. A lot of people didn't really believe that Anthropic could actually provide us with a context window that large, or that the model could use it effectively. And
Open source software is changing, and there's a new strain / a new breed of tooling: Extremely Personal Software (EPS). Skilled programmers will reap most of the benefits, while the market adjusts and people figure out how to bring this new workflow to the masses.
This is going to be a really short one. I'm a bit of a purist when it comes to my Claude code setup. I protect my context window like a gated garden. I don't like the idea of "skills", "memories", most MCPs,
My preferred use of A.I. for programming is Claude Code, planning mode sometimes, almost never auto accept edits. Go slowly, don’t put on the ring, hide from the eye of Sauron at the top of the tower. Stay vigilant against the doom tabbing. Exercise your will. Take breaks
Over the last week or so I finally tried Claude Code. Every $%&#'ing time I try to use it, it tries to test the API with: curl -s http://localhost:3000/api/v1/... To which I have to interrupt it and remind it that my app is running
Hello Slam Dunk Software readers! It has been a while. I'm sorry. While I believe I'm destined to write rust, go, and other based technologies, I'm currently forced to put up with Python. But despite this thorn in my side, it has been nice
What are the signs, for you, that text was generated by Artificial Intelligence? My first big run-in with this was when I was exploring GPT-4 through writing fantasy, and every other sentence included the phrase, "weaving a tapestry". ChatGPT had some kind of weird, sycophantic relationship with tapestry
A lot of people add unnecessary preambles to their LLM prompts—and that’s what this post is pushing back on. Sometimes it's a simple— "Please don't hallucinate" or... I knew someone who prepended every prompt with a 200-token manifesto: "When responding, focus
Donald Knuth is quoted as saying: Premature optimization is the root of all evil. Today we're going to chase that thread. In doing so, we're going to uncover the story of when Donald Knuth "skill-issued" Edsger Dijkstra. But first we have to figure out—
There's a new pope, and he's from Chicago! He's not just the first pope from the windy city, but, as you might've heard, he's the first North American pope, ever. LET'S GOOOOOOO 🦅🦅🦅 🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸🦅🦅🦅🦅🦅🦅🦅!!!!!!!!!!! No, but seriously, this marks a
SpacetimeDB is a unique "database", written in Rust, that was developed by Clockwork Labs, and a month ago made a bit of a splash with their promotional video. It's available on GitHub under a BSL 1.1 license. (This is notably not open-source, but instead source-available.
Lamenting The Enshittification of Substack The wave of enshittification has finally reached the shores of Substack in the form of Substack Reels. Yes—the attention-machine has scaled the ivory tower of our once peaceful platform, taken a big dump, and in its wake has left us with an endless supply