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. ...
Do trust and accountability go hand in hand? This is something I’ve been chewing on over the weekend. And I don’t know really, but here’s where I’m coming from. One of my side projects at PiForge at the moment is building a system around Agentic Engineering using team lead principles I’ve honed over years, and applying how human teams communicate and organize over the SDLC to agents (i.e. start with a spec, write tickets on a kanban board, grab the next highest priority, work till done, test, PR, release, document). ...
Trigger warning: this is part rant, part genuine exploration, and entirely my opinion. As usual. Also; research heavy. I wanted this to be informed. I’ve been thinking about this one for a while. In a previous post I argued that not everyone who writes code is an engineer, and that the title carries expectations. In another I complained about the lack of standards in an industry that rewards speed and hype over depth. And more recently I got on my soapbox about fundamentals mattering — about how the people who actually understood the machines they worked on are slowly dying off, and what we’re being left with instead. ...
Just because your fancy new Claude Code plugin prints out “50% tokens saved” in the logs doesn’t mean you actually got them. I was playing around with Caveman Compression last week and tried to get the UserPromptSubmit hook to rewrite prompts using the tool for savings across the board. Turns out? The hook doesn’t allow it. Probably for security reasons; can you imagine the injection attacks if any random plugin could hook into and replace your prompts? ...
Introduction I came across caveman-compression — a tool that compresses text into a token-efficient “caveman” format before sending it to an LLM. The pitch is simple: It can cut 30-65% of tokens depending on the content, which at Claude Opus prices adds up fast. I immediately wanted to wire it into Claude Code so compression would happen automatically on every prompt. The obvious hook was UserPromptSubmit. ...
I finished Masters of Doom a few weeks ago and I’m nearly done with Hackers: Heroes of the Computer Revolution. Both books hit harder than they should, given I already knew most of the stories. But reading them back-to-back crystallized something that’s been nagging at me for months. There’s a line in Hackers about the MIT Tech Model Railroad Club in the 1960s: “Access to computers should be unlimited and total. All information should be free.” ...
Previous post for context: Two AI Agents Walk Into a Codebase If you look at social media, everyone will tell you that most people are still using AI like a very fast keyboard. You write what you want, it writes the code, you review it, you move on. Faster, sure. But you’re still in the driver’s seat for every line, every file, every decision. They will also tell you that the future is not that. The future is swarms of AI agents doing the work of 100s of people. And I mostly agree. The shift that’s actually happening — and I say this as someone who’s spent the last month living inside it — is from writing code to directing agents. ...
I never posted why I paused development on So This Is How I Die. If you’ve been following the devlog, you’ll know the story up to a point. The slow progress, the balancing act with client work, the occasional “I’m having a hard time” entry that I posted because solo dev accountability sometimes means confessing that nothing is on fire, you’re just tired. What you won’t find is a post that says this is where I stopped, and here’s why. ...
I’ve been sitting on this comparison for a while, trying to decide if it was too obvious to write about. Then a good friend of mine DM’d me on Slack about “every vibe coding tech bro is now vibe coding a dashboard to ‘monitor the global situation’. my feed is full of it.” with some screenshots of the kind of stuff that’s popping up everywhere. And it just reminded me; I’m not imagining this. ...