Here’s a tiny, stupid problem that has stolen an embarrassing amount of my life: I plug a BrightSign player into my network, it grabs whatever dynamic IP the UniFi controller feels like handing out, and now I have to go find that IP before I can SSH in and do actual work. Claude skills and a new tool to the rescue!
Somewhere in the last year, a bunch of us who hadn’t shipped real code in years quietly started shipping again. Not reviewing it. Not architecting it in a doc and handing it off. Actually building it. And loving it.
I’ve been teasing this for a while. Time to stop teasing. Meet Gorai — a modern, open-source robotics framework written in Go.
Most people think of a BrightSign player as the little box behind a screen that loops a video. That’s true right up until you realize the thing is a full ARM64 Linux computer with an NPU sitting idle most of the day. And you can run your own code on it. Natively. That’s what an extension is, and once you grok it, a whole world opens up.
Python won because it was easy. That was the whole trick. And now, in the age of agentic coding, that trick has stopped being an advantage — and quietly became a liability.
Last post I showed off the chainsaw I built myself — my build-autonomous loop, the padded room, the whole rig — and cut down a little tree with it: a Go CLI to boss around a smart plug. It was well worth building! I also think you should probably stop building your own. Yes, including me. Especially me.
People keep asking me how I actually work with Claude Code now. Not the “does AI coding work” question — I’ve beaten that horse into glue on this blog already — but the boring, practical, how-does-my-loop-actually-work question. So here it is. The whole rig. And fair warning: what I’m about to describe is a chainsaw, and most of the industry is still lined up at the axe-chopping contest.
I just spent a few days at a retreat on the future of software development. Small rooms. Unconference format. Some of the sharpest people in our industry - the kind of names that show up on the spines of the books on your shelf. I’m not going to tell you who was there or who said what. We ran the whole thing under Chatham House Rule: use what you learn, attribute none of it. This is my initial take-away.
Here’s a question I can’t stop chewing on: why is some software so damn good, and most of it so… not? Not buggy. Not slow. Just bad. Bad in a way you feel in your gut the moment you touch it. The answer isn’t tooling, or budget, or headcount. It’s taste. And I’m starting to think taste is the whole ballgame in the age of AI.
A couple weeks ago I wrote that your organization has to learn as fast as your best AI adopter. Externalize, combine, socialize, internalize. Run Nonaka’s spiral or get left behind. A bunch of you wrote back with the same question: okay, but where does the knowledge actually go?
Everyone is asking the wrong question. “How do we adopt AI agents?” “Which tool?” “What’s the right policy?” Wrong questions. The right question is: how does your team turn what one person learned on Tuesday into something everybody on the team uses by Friday?
Next week I get to watch one of my favorite things: see a room full of smart people handed a hard problem and watch them figure it out in real time. I’m headed to InfoComm to mentor, judge, and sit on a panel for an idea sprint about AI at the edge. And I could not be more excited.
A response to “LLMs are Eroding My Software Engineering Career and I Don’t Know What To Do” - and to everyone I keep hearing this same anguish from. You’re not wrong that the ground is moving. You’re wrong about which ground.
There’s a thing going around the engineering blogs and Hacker News right now: AI killed Agile, Waterfall is back, write your specs up front, welcome to “Waterfall 2.0.” You may have seen the Medium piece titled Agile Is Dead. AI Killed It. Welcome Back, Waterfall.. Hmmm.
And once I followed the logic far enough, I ran into a second question that nobody seems to want to answer out loud: if the agent writes the code, who actually reads it?
I’ve been dorking around with local AI coding agents for a while now. At some point curiosity got the better of me and I had to know: what the heck are these things actually doing under the hood?
In recent years, digital signage has become a solved problem: push content to screens reliably, at scale, on schedule. That’s not enough anymore. The market is now demanding screens that perceive — that understand what’s in front of them and respond in real time. Most of the hardware deployed in the field today will fail at that job because the foundational assumptions are wrong. Here’s what’s actually required and why the infrastructure choices you make now will define your deployment for the next decade.
A recent industry retreat of senior engineering practitioners published their findings on where software development is heading. Reading it felt like someone had been reading my mind — and the minds of the people I follow online — and synthesized it all into one document. When a lot of people arrive at the same conclusions independently, that’s signal worth paying attention to. Here’s my take on each major theme.
The era of fixed-fee AI spending just ended. If you’re a CTO or engineering leader and you haven’t noticed yet, you will very soon — probably around September 2026 when some budget alerts start firing.
There’s a reckoning coming for a specific type of software engineering manager. Not the good ones. The ones who turned themselves into human Jira routers. The ones whose primary skill is translating documents into tickets and running standups. Those jobs? Gone. Faster than you think.
Look, I’m going to be direct here. If you are not using AI agentic coding methods right now - today - you are going too slow. Not “a little behind.” Not “maybe missing something.” Too damn slow.
Open source is about to get a lot messier. Not because the code is getting worse – because AI agents just changed the economics of “fork it and fix it yourself.”
The AI models are good enough. There, I said it. The bottleneck isn’t the model anymore – it’s how you use it.
Grace Hopper built the first compiler in 1952. They said “you can’t make them understand English-like instructions.” She had a running compiler and nobody would touch it. Sound familiar? Grace had some thoughts about this kind of thinking. She had a lot of thoughts, actually.
From a certain point of view, there are two kinds of people in the world: builders and not-builders. This isn’t judgment—it’s observation. Some people consume. Others create. Builders can’t help it.
AI has made code cheap and abundant. The scarce resource is now knowing what to build, not how. This is creating a rapid split between companies that sell workflows and companies that sell capabilities. Only one of these will survive.
A Scottish football manager once said, “Some people think football is more important than life. But they are wrong. It’s much more important than that.” When intelligence becomes a utility, the ability to ACT on it becomes everything. In today’s software world, Agency is more important than anything else!
The AI train has left the station. Some of us are on board, generating entire modules from specs. Others are still on the platform debating whether the train is even real. Four smart people wrote about this shift this past week. They all agree on what it means. And I agree with them.
If software changes something in the real world, it’s a robot.
Software development is stratifying into three distinct tiers. Where you land will determine whether you make more money, the same, or far less than today.
Looking back at 2025, one theme dominates: AI agentic programming went from novelty to necessity. This year transformed how I think about software development, career advice, and even my personal hardware projects. Here’s what I wrote about, what I learned, and what I expect in 2026.
Five factors now drive language choice: developer adoption, job market demand, LLM code generation quality, concurrency handling, and deployment complexity. Here’s how they intersect.
“We are nearly at coder-equivalency for economically useful coding. A sufficiently experienced software engineer can now write >90% of production-ready code purely through prompting.” Yes, exactly.
I let Claude Code do whatever it wants without asking permission.
Before you spit out your coffee: I keep it in a jail. A container jail.
I don’t like the term “vibe coding.” I strongly prefer “AI-assisted software engineering.” But regardless of what you call it, Gene Kim and Steve Yegge have written a book about it - and their journey from skeptics to true believers is the most interesting part.
In my previous post about Claude Code, I talked about using VS Code devcontainers to safely run Claude in “dangerous mode.” That was great for a typical software project. But what about something harder? What about porting a complex hardware-interfacing library from Python to Go, where you need to deeply understand USB protocols, radio registers, and firmware internals?
That’s exactly what I did with gocat – a Go library for controlling the YardStick One sub-GHz RF transceiver. And Claude Code was instrumental in making it happen.
So I’ve been working on this project called client-w-mcp – it’s a leanring project to truly understand how an AI agent works with MCP servers. And I’m exploring Agentic development - with Claude Code. Why Claude Code? The first time I used it, Claude just… flowed. It seems to do a lot more by itself to figure things out. I especially like the Task() so that it can go do more than one thing at a time.
There’s a lot of folks who are in outright denial about AI agentic programming. They are wrong. AND… they are right. My thoughts.
There’s no way to really understand something unless you dive into first principles. This is especially true for AI coding agents. What is the editor doing under the hood? I try to peel the onion a bit.
I’ve been exploring the intersection of AI and content creation lately, and I wanted to share my experience using Anthropic’s Claude 3.5 AI assistant within the Zed editor to streamline my blogging workflow.
Reading time: 10 minutes
It’s brutally hard to find a job as a new college grad today. And AI is changing things even for seasoned Engineers. Here’s my advice.
The evolution of AI-assisted programming has reached a pivotal moment, transforming from simple code completion to truly collaborative AI agents. This shift represents not just an improvement in tooling, but a fundamental change in how software is developed.
I bought the eBook AI at the Edge. But you can download a free copy from LinkedIn. In short? Don’t waste your money. But for free?
Let’s talk about AI pair programming - not the hypothetical future version, but what we have right now in 2024. I’ve spent the last year working extensively with AI coding assistants, and I have some thoughts to share.