Skills on Greg Herlein

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

Tue, 22 Sep 2026 00:00:01 -0800

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.

Harness Engineering Has a Name Now

Mon, 07 Sep 2026 00:00:01 -0800

A room full of CTOs and architects met in a Swiss village this summer and, without quite meaning to, gave a name to the thing I’ve been quietly building for months. They call it harness engineering. I’ve been calling it “the tooling is the new model.” Same animal. And the part they flagged as unsolved, I think I’ve got a first, opinionated stab at.

Re-use your skills across all your coding agents

Sun, 23 Aug 2026 00:00:01 -0800

I use more than one coding agent. Not because I’m indecisive — because I’m testing different agents - and learning how they work - and the field is moving fast. Seems like a new one every week! But every single one of them wants skills in its own directory, and I got tired of cp -r and stale copies. So I wrote a tool.

Hey Claude, Set the IP address and name for the new BrightSign Player?

Sun, 19 Jul 2026 00:00:01 -0800

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!

The Chainsaw I Built Was for Learning. Superpowers Is for Scaling.

Sun, 05 Jul 2026 00:00:01 -0800

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.

A Chainsaw at an Axe-Chopping Contest: My Current Agentic Loop

Fri, 03 Jul 2026 00:00:01 -0800

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.

Procedures Travel. Knowledge Stays Home.

Thu, 25 Jun 2026 00:00:01 -0800

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?

AI Agent Naysayers

Tue, 17 Jun 2025 00:00:01 -0800

There’s a lot of folks who are in outright denial about AI agentic programming. They are wrong. AND… they are right. My thoughts.

Agent Building: Ollama Hosted Models Token per Second

Sun, 15 Jun 2025 00:00:01 -0800

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.

Advice to New Developers (or, How to Get Hired)

Sat, 31 May 2025 00:00:01 -0800

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.