Ai

I think AI is ushering us into the 3D printing era of software. I’m sure others have had this thought too, but it really hit me this morning during a conversation with a colleague. When 3D printers became affordable, people predicted the end of manufacturing. Everyone would print everything at home. Why buy a product when you can just make it? But that’s not what happened. Far from it. Most people still don’t own a 3D printer. Of the people who do own one, they mostly print models someone else designed. Only a small group actually opens up CAD and designs their own parts. And nobody’s printing their own fridge. ...

I read a post on the Haskell Discourse this week that I haven’t been able to stop thinking about. It’s called How to keep enjoying programming in a world of LLMs, written by a developer who goes by turion, and halfway through I had that slightly uncomfortable feeling of reading something I could have written. Or at least, something I’ve been circling for months without quite landing on. Go read it. It’s long, it’s thoughtful, and it’s (by the author’s own declaration) 100% human written. Which, these days, is worth mentioning. ...

Most of my life I used Windows for gaming, and Linux for development. When I started my first full time job in 2007, they gave me a Windows desktop for Java dev, and I hated it… In 2010 they added a BYOC policy and two devs I worked with convinced me to buy my first ever Mac, and since then, that’s what I’ve been using. Mainly because I dialed in my perfect setup early, and migrating an old Mac to a new Mac is super easy, and once I got my iPad and eventually settled on iPhone (after jumping between that and Android every 2 years for a while), I was locked into the ecosystem, and no matter how much it gets enshittified, I just haven’t been able to migrate away (and I’ve tried, quite a few times). ...

I was on LinkedIn this morning making a quick post about my experience with Omarchy, and then this showed up in my feed. “Local dev setup makes zero sense to me now.” It’s a comment from Matt Pocock, who we all know by now, the TypeScript educator, creator of the /grill-me skill that half the industry has been grilled by at this point (including myself), with a clip from The Pragmatic Engineer podcast. The post goes on: every dev has a hundred terminals, those terminals should be available to your whole organisation, available from everywhere. So for him that means he’s on a train chatting to his Hetzner box in Discord, and therefore an expensive laptop feels like wasted compute. ...

Background Okay, so this post is a follow up to a few different posts, but most notably The Token Saving Cake is a Lie. Before reading this one, I highly recommend checking that out first. Go ahead. I’ll wait. Back? Good. Let’s continue. Headroom So I said that the solution is probably something like Lynkr, but before building the integration, I discovered Headroom (45k stars, Python, its own trained compression model, ships RTK as a component). It does everything the Lynkr plan described, supposedly better. Set ANTHROPIC_BASE_URL=http://localhost:8787, run headroom wrap claude, done. ...

Previous posts for context: The Future of AI Coding is Directing and C.A.S.T Progress: First Blood Last time I had one event flowing from a ticket board to a NATS topic. That was the plumbing. This time the plumbing has something running through it: a ticket goes in one end as a one-line wish, and a reviewed, merged, cleaned-up branch comes out the other. No human types a line of code in between. ...

Tools Full comparisons and context in my 2026 AI tech stack post. This is just what you need installed to follow the workflow below. Claude Code If you’re new, start with the cheat sheet and Anthropic best practices. Security — set this up first: Claude Code Security Hooks — 7-layer prompt injection defence, read guards, canary files Lock down your .env and any git-secret files in .claude/settings.local.json before anything else MCP: Context7 — library/API docs on demand DeepWiki — open source repo documentation Skills: ...

Previous post for context: The Future of AI Coding is Directing. Let Me Introduce You to Your C.A.S.T. Also, this banner was generated by ChatGPT and whatever model they are using at the moment, and I’m kinda impress, NGL. When I wrote about C.A.S.T last month, the design was solid but unproven. I had a SPEC, ADRs, hire/fire scripts, and a lot of conviction. What I didn’t have was a single event flowing from a ticket board to a NATS topic to a waiting agent. ...

Introduction In some ways, a lot has changed since my last post, and in other ways, not much has changed. There has been a big shift in the last 12 months, especially toward “agentic engineering” and how we run multi-agent AFK setups vs HITL as we have been. I touched on this in my introduction to the tool I’m working on as well, which, spoiler, is part of my toolchain. Kinda. It’s a WIP… ...

I have not been “AI pilled” yet. (Also, what a stupid term.) While AI has become deeply integrated into my workflow, and I genuinely love having agents run things for me in the background while I focus on other things, I wouldn’t say I’ve had some red pill moment where “I see the truth now” and AI became an essential and daily thing… You see, my morning routine when I start work is the same: I open my terminal of choice (Warp), and I open my IDE of choice (whichever JetBrains one is applicable). And then if the task deems it, I’ll open Junie or Claude inside my IDE. ...