Give Your Agent Exemplars

Finding ways to learn with AI is critical. This blog describes how to give your agent exemplars to facilitate learning and higher quality work.

What it's Like Learning with AI Tools

About three years ago I wanted to learn electronics. I was motivated by a project idea where I wanted to go all out in a custom lighting system around my desk. I had a vision in my mind for how it should work, but the electronics aspects of it were

Why the AI Wall Keeps Moving

There has always been doubt that AI will continue to progress. One such argument was that as the length of tasks AI is solving increases, compute and the techniques used to train the models will not be able to keep pace. The empirical reality has ended up showing that AI progress continues.

How much AI does $10k get you? (Local LLM, May 2026 Edition)

In the last month there have been non-stop open model releases which trade blows on benchmarks against recent frontier models. However, local models often outperform on benchmarks, and underperform on real world tasks (1, 2). There's a whole host of reasons for this, but one that is

Turning the Dark Factory Lights On

Update 04/24/2026: This blog was written for version v0.13.4 of Gas City released at the end of March. Since then Gas City has moved to version 1.0. I would recommend checking out Steve's blog about the release: Welcome to Gas City Agents finally

Is a Mixture of Models a Competitive Advantage?

More choice seems better, right? Turns out that is the case, but it comes with a cost, and not necessarily a monetary one.