The Em Dash

Less Theory. More Button Pushing

Get New Posts

Real AI implementation stories. What worked, what didn't, and the buttons I actually pushed.

Your $240 Question: When Should You Actually Try the Hot New AI Tool?

The Hook Here's a question worth $240: When a viral AI tool drops on tech YouTube, how do you decide whether to spend time exploring it? I'm asking because I was seconds from midnight on this one myself. Clawdbot (now OpenClaw) hit my feed—autonomous AI

Feb 2

Local LLM Setup Was Step One. Finding the Right Model Was Step Two.

In my last post, I walked through setting up a local LLM on an HP Z2 Mini. I got Qwen3-Coder-32B-Instruct running and called it success. Then I actually tried to use it. [Cue lab coat and clipboard] The Test That Broke Everything I gave Qwen a simple task: "Here

Jan 28

I Built an Unlimited AI Workspace (And Why You Might Want One)

Look, I'm not going to pretend this was purely a practical decision. I like tech. I like new toys. Any excuse to justify new hardware is a good excuse for me. But the reason I could actually justify pulling the trigger on a local LLM workstation? Subscription fatigue

Jan 15

I Have Nothing to Show: Three Months of AI Work With No Artifacts

I officially started as Director of AI Enablement on January 1st. But I've been working on this since October. And I still have nothing tangible to point to. Here's the honest truth: I officially start as Director of AI Enablement at an MSP on January 1st,

Jan 8