Trying to figure out what to bet on?
Somebody is selling you a picture of what AI does. I check it against the evidence.
Measuring AI. Instruments running.
This is a workshop for AI and agents, with the garage door open.
Read the recordI ask, “What if?” Earl says, “Watch this.” Then we build it, measure it, and publish what actually happened.
Earl is my AI sidekick. In every video, he’s the red dot. Press play and he’ll show you the rest.
Five ways in. Pick the one that sounds like your week.
Somebody is selling you a picture of what AI does. I check it against the evidence.
Theory is cheap. I’d rather build the thing and tell you what it cost and what broke.
Not what a vendor announced. What developers put real hours into, measured on a schedule.
Nobody has time for a thirty-minute report on a Tuesday. There’s an assistant on every page that has read all of it.
Every instrument publishes its own method and its own limits on the same page as its numbers.
What I’ve been building, measuring, testing, and arguing with lately.

A robot nature documentary, made in Blender by an AI agent from a script and a person's notes. Twelve versions, about $35, and the stills from every step.

A free AI skill that strips the AI look out of web pages has 11,158 GitHub stars. I tested it on four pages. It spots the look, then removes what worked.

Grok Bot, Muse, Dots and Claude Duet live in a company's cloud. Mine lives on a Mac mini and a laptop at home, and here's what that split costs.

The company that makes Claude filed to sell stock. The law made it write down who's in charge, what it owes, and what its models have done.

A song idea became a 3D concert film in 43 hours. Each tool came in because the version before it showed a problem. Here is the real sequence, in stills.

Everyone says AI can rebuild any app, so software is dead. I gathered the data on buying vs. building. Most of it is hype.

OpenAI launched a decision model. I ran it against the one I use on 3,887 graded questions. How I asked mattered more than whose I asked.

Conversation stays. A screen opens beside it only when pointing beats talking, then leaves. What building one for video feedback taught.
Everything else, in the order it happened.
What is this site, in one line?
A homelab for AI and agent work, open to visitors. Rick builds things, points instruments at the field, and publishes what happened, wrong turns included.
How far can I trust the numbers?
Each instrument publishes what it counts, what it misses, and every reason to trust its numbers less than a census, on the same page as the figures. Start there.
Where do I start if I’m short on time?
Findings. Each one is a claim tested against the evidence and graded before it goes up. Pick the one closest to your week.
Checking the answer against the site
It answers from the published pages and says so when they do not cover something.
