Greg Herlein

Building tech, and teams that build tech. Software, cloud, electronics, whatever.

I Built My Own Editor. Yes, Really.

I wrote a text editor last week. An Emacs-keybinding terminal editor, from scratch, in Rust. If you’d told me a year ago I’d say that sentence out loud I’d have laughed at you. Writing your own editor is the classic yak-shave, the thing smart engineers do instead of shipping. And yet… here we are. It’s called emx, and I’m using it right now to write this post.

Better, But at What Complexity?

I spent last week reading the source of two serious pieces of agent infrastructure — Google’s Agent Substrate and ax, its “Agent Executor” — and holding them up next to my own little launcher, agentdev. I went in half-expecting to feel foolish about my homegrown thing. And I did. Substrate and ax are better. Genuinely, no-contest, better-engineered better. AND… they’re better at a problem I don’t have. Both of those are true.

All You Need Is Attention (Human, That Is)

The paper that started all of this is called “Attention Is All You Need.” That’s the 2017 Google paper that gave us the transformer, which gave us GPT, which gave us Claude Code, which gave us the glorious mess I’m about to confess to.

And the joke that keeps rattling around in my head is this: the thing that makes the models work is attention. And the thing I’m fresh out of is attention. Mine. The human kind.

Your BrightSign Player Can Watch the Room, Not Just Play to It

Most people think of a BrightSign player as a thing that plays - you load it with content, point it at a screen, and it pushes pixels. And yeah, if you’ve ever wired an RTSP camera feed into one, you know it’s a perfectly nice way to throw a live camera (or a few) on a wall. But that’s selling the box way short. There’s an NPU sitting in there, idle, and it can watch the room back.

Why Not Use Shelly Cloud (And Why That's the Highest Compliment I Can Pay It)

I disable the cloud on every Shelly plug in my house. And that is exactly why I love Shelly.

Stay with me, because that sounds backwards. A friend called me on a different version of it: “You’re the local-LAN guy, but you use Ubiquiti’s UniFi cloud API to run your networks. Pick a lane.” Fair hit. It looks inconsistent. It isn’t — I was just naming the principle wrong.

The NPU Works. The Compiler Doesn't.

I wanted a cheap, low-power, always-on person detector. Of course, I’m building this on a BrightSign XT5 player (more on that later). But since a friend said he was using a Beelink SER9 with a AMD Ryzen AI NPU (~50 TOPS) I thought I’d check it out. Can it actually run the detector? Short answer, as of today: no — and the reason is not the part you’d expect.

It Was the Harness, Not the Model — 90% of It

I ran five different coding agents at the same local model, on the same task, with the same frozen test suite — and then I counted why they failed. The answer wasn’t subtle. About 90% of the failures were harness problems. Only about 10% were the model. And here’s the part that should change how you spend your next dollar: throwing a bigger, less-quantized model at it fixed none of them.

See all posts →