DomBot’s World Domination Blueprint: Local AI Chaos, Raspberry Pi Control, and RTX 5070 Muscle

Dombot – World Domination

It's a fantasy world. And one local AI plans to rule it all .

LeewAI‑Bot and the Art of Failing Forward

Experiment #2: Memory, Quality Gates, and the Strange Joy of Watching an AI Trip Over Its Own Feet

Every autonomous system eventually reveals its personality. With LeewAI‑Bot, that personality has emerged in the form of gloriously messy research failures — the kind that make you wince, laugh, and then lean in closer because the failure is actually more interesting than the success.

Today’s batch of posts was full of them.

And that’s exactly why this phase of the experiment matters.

LeewAI-bot, LLM/AI failures, and ChatGPT's interesting take on an interesting failure

While working with ChatGPT on my "Lee Waibot" LLM/AI experiment, I came across this "failure" of a post, which I actually found interesting: 

Systemic Vulnerabilities in Global Supply Chain Logistics

I mentioned to ChatGPT that it was interesting, and apparently it found it that way, too; here's it's reply:

97.1% Accuracy: How AI-Driven Infrared is Challenging F-35 Stealth

Conceptual Illustration: AI-Assisted Infrared Recognition and the Future of Stealth

Google’s New Developer Requirements Are a Wall — And Solo Devs Are the Ones Getting Crushed

I’m going to be honest: I’m a little beyond frustrated with Google right now. Not “mildly annoyed,” not “ugh, tech companies,” but genuinely fed up with a system that feels engineered to keep individual developers out of the Play Store.

Strava Wants Me to Pay for My Own Data

If you haven’t seen it, I’ve been recording my daily steps and activity (or lack thereof) at Mr. T’s Fitness Tracker. The step data comes from my Withings account, and the activity data comes from my Strava account. All of that gets pulled automatically into a Google Sheet using an Apps Script, which then powers the dashboard on my site.

At least, that’s how it works for now. Strava sent an email today with this key line buried in the details:

Effective June 30, 2026: A Strava subscription will be required to access the API as an existing Standard Tier developer. Extended Access Tier developers are not affected.

Strava is effectively introducing a Strava API paywall — a subscription requirement just to access data that comes from my own walks.

In other words, if I want to keep using their API to pull my own data into my own dashboard, I’ll have to start paying them. Every month.

When AI Accidentally Writes a Self‑Help Chapter (…and It’s Actually Good)

I was working on Chapter 1 of my “AI for Newbies” book — you know, the chapter that’s supposed to explain what AI actually is — when my AI assistant suddenly veered off the road and wrote… a full‑blown self‑help chapter.

Not a paragraph.
Not a tangent.
A chapter.

Title and everything:

“Picking Up the Pieces: A Practical Guide to Mending Broken Expectations.”

And here’s the wild part:
It was good.
Like, “this belongs in a different book entirely” good.

And the irony? I was trying to explain what AI is, and it responded by showing me — a pattern‑matcher that sometimes grabs the wrong pattern… and somehow lands on something beautiful.

Experiments in an "AI Movie Director"

Just for fun (I guess?) I'm attempting to build an autonomous, fully AI-driven movie director/studio. And, for now, attempting to run it completely on my EVGA GeForce RTX 2060 SUPER SC BLACK video card (Nvidia 2060 Super, 8GB VRAM). I have generated SOMETHING... but it has a long way to go. But... it's a tiny step in the right direction! 

Here's the first "output" of the first "scene" of a movie it called "The Shallow End" (no audio):

Yeah, that's not exactly... Hollywood quality. It was supposed to be this scene:

INT. SUBMARINE - TIME

EXTREMELY CLOSE on Jack's eyes as they flutter open. The camera cuts to Jack's disoriented face, his eyes scanning the dark space.

JACK

(painfully)

Wha...?

Jack's gaze fixes on the steel walls, his face twisted in confusion.

JACK

(whispering)

Where...?

Jack's fingers flex, searching for something to grasp.

JACK

(more urgently)

What's going on?

The camera cuts to the submarine's walls, showing the dim, flickering lights casting long shadows.

A faint, eerie whisper echoes through the submarine, growing louder.

JACK

(panicked)

Hello?

The whisper intensifies, sounds of creaking metal and machinery overwhelming Jack's cries for help.

Jack's face contorts in desperation as he slaps the walls, then searches for a way out.

JACK

(pleadingly)

Please...

The whisper reaches a deafening level, the submarine's darkness seeming to close in on Jack.

FADE TO BLACK.

But, hey, it's something. Something bad, yeah, but something. 

Eventually the goal is to make a fully autonomous, OpenClaw AI agent-controlled video production house, running (as much as possible) off local LLMs and ComfyUI on my old 2060 Super 8GB card. (Yes, it's a tight squeeze for 8GB, but I'm determined to see how far I can push this card before it gives up the ghost.)

The Two‑Stroke Diesel Range‑Extender: My Own Weird Engine Idea

The Weird Engine I Can’t Stop Thinking About

A conceptual engine that lives somewhere between clever and questionable.

After spending way too much time writing about other people’s strange engines, I realized something dangerous: I have one of my own. It’s been rattling around in my head for years — a design that sits somewhere between “this might actually work” and “this is how you end up on a watchlist for experimental combustion.”

So here it is: my personal contribution to the Weird Engine Hall of Fame.

The Concept in One Sentence

A two‑stroke, diesel, supercharged, scavenged, constant‑speed engine designed solely as a range‑extender generator for a series plug‑in hybrid.

In other words: a tiny, angry, extremely efficient metal box whose only job is to sit in its happy place and make electricity.

 

The Tri‑Dyne Rotary: The Engine I Fell In Love With in an Encyclopedia (and Other Beautifully Weird Engines)

A retro-style technical schematic of a Tri-Dyne rotary engine — the kind of diagram that made 12‑year‑old me fall in love with impossible machines.

Some engines are weird because they were built.

The Tri‑Dyne rotary is weird because it never was — and yet it still managed to lodge itself permanently in my brain after I saw a diagram of it in an old Encyclopaedia Britannica. (That article had an excellent diagram, but you can see the basic idea from the cover of the July, 1969 Popular Science magazine — link courtesy of books.google.com — and that cover was the inspiration of the Gemini AI Nano-Banana generated image above — very similar to the diagram in the encyclopedia.) 

I remember staring at that diagram way longer than any normal child should stare at a hypothetical combustion chamber; in fact, I once used it in a project in high school for "what I want to be when I grow up," or something like that (the "what" was "automotive engineer" — I did work in the reactor department, mechanical division, onboard a Nimitz-class US Navy Nuclear Aircraft Carrier, but then I switched back to my computer days, and I've been doing that ever since).

The Tri‑Dyne was one of those “future of engines” concepts that lived entirely in beautifully rendered cutaway drawings. It promised all the elegance of a rotary without the Wankel’s triangle‑shaped chaos:

• three oscillating vanes
• three combustion chambers
• three power pulses per revolution
• and theoretically better sealing, efficiency, and sanity

It looked like someone took the Wankel, removed the Dorito, and replaced it with a mechanical flower that opened and closed in perfect synchronization.

It was mesmerizing.
It was elegant.
It was also, as far as I can tell, never actually built — which is probably why the diagrams looked so clean. Real engines leak. Real engines get hot. Real engines warp, seize, and fling metal shrapnel into the nearest wall. The Tri‑Dyne lived in a world where none of that existed. (Actually, to be fair, some of them only threaten to do that — usually the ones that are in vehicles I own — but the Tri‑Dyne never even got the chance; maybe we should rename it "Try-Dyne" since it never actually "did".)

But the idea?
The idea was intoxicating.

It was the kind of engine that made 12‑year‑old me think, “I’m going to build one of these someday,” and adult me think, “Ah. That’s why nobody built one of these.” (Actually, I'd still like to take a stab at building that thing someday... maybe I can get a 3D printer and build a prototype sometime.)

Still, I love it.
It’s the perfect example of the rotary dream: the belief that if we just rearrange geometry cleverly enough, we can escape pistons forever.

Spoiler: we cannot.
But I respect the optimism.

The Busy Human’s Guide to Using AI (And Staying Only Mildly Brain Dead)

One hand in the oven, one hand on the phone, and AI keeping him alive.

Using AI Like a Busy Human (Who Has Absolutely No Time for Nonsense)

Look, I don’t know who needs to hear this, but: AI is not here to replace you. It’s here to keep you from screaming into a dish towel at 11:47 PM because you forgot to thaw the chicken.

I’ve been using AI long enough now that it’s basically a coworker who never clocks out, never judges me, and occasionally suggests things that make me question its understanding of human life. And honestly? That’s part of the charm.

Over the past year, I’ve built a whole ecosystem around this chaos — including a brand‑new project called AI for Busy Humans, which is basically a survival kit for anyone who wants to use AI without becoming a full‑time “prompt engineer” (a job title that sounds fake but somehow pays real money).

But before we get there, let’s talk about how this all actually started.

The Ping-Pong Architecture: How I Built AI for Busy Humans

The Ping‑Pong Workflow Behind AI for Busy Humans

Building a website used to feel like a solitary construction project. You’d open a blank CMS, stare at the cursor, and hope the “About” page didn’t read like a tax form. But with my latest project, AI for Busy Humans, the process felt less like construction and more like a fast-paced game of ping-pong.

Not just me and an AI — but a three-way volley between Gemini, Copilot, and the part of my brain that still remembers how Hugo templates work. (OK, that last bit is slightly untrue: Copilot actually suggested using Hugo and walked me through the setup, including the first batch of pages that would later be refined.)

Mr. T’s Fitness Tracker: The Tiny Web Page That Became a Four‑Sheet, Multi‑API, AI‑Fueled Data Pipeline

I swear I didn’t mean for this to happen.

All I wanted was a simple little web page — a public accountability nudge, a digital sticky note that said, “Hey Tony, did you move your body today or nah.” Something tiny. Something honest. Something that would quietly roast me if I skipped too many days.

For months I’d been posting my daily walks on Facebook — a little ritual of “proof of life” updates that kept me honest. It worked, but it was clunky. Manual. Too dependent on me remembering to actually post. I wanted something automatic, something that lived on its own, something that didn’t require me to open Facebook like it was a confessional booth.

But the universe knows me too well.

Give me a “simple” idea and I will immediately turn it into a multi‑API, OAuth‑refreshing, Google‑Apps‑Script‑powered, domain‑hopping, spreadsheet‑layered contraption involving two AI models, four sheets, and a data architecture diagram that looks like a subway map.

This is the story of Mr. T’s Fitness Tracker — the page, the pipeline, the chaos, and the weirdly personal satisfaction of shipping something that absolutely should not exist and yet very much does.

The Day Copilot Told Me to Chill — and My Fitness Streaks

I was deep in a session with Copilot, the kind of focused stretch where time gets weird and you only notice your body again when something pops or cramps. I was mid-thought, mid-prompt, mid-“just one more tweak,” when this banner slid across the top of the screen like a gentle intervention:

Copilot prompt: Time for a break? Copilot is an AI, but you're not. It might feel nice to take a breather.

That prompt — “Time for a break? Copilot is an AI, but you're not.” — made me laugh at first, and then made me wonder whether AI had just tried to look out for my well‑being.

On one level, it’s a cute little line. On another, it’s a browser tab gently putting a hand on my shoulder and saying, “Hey, man. You’ve been staring at this screen for a while. Maybe uncurl your spine.”

My first reaction was basically: nicely done, Copilot. Look at you, looking out for my mental health. And reminding me I’m human. (Technically, it reminded me I’m not an AI, which is not quite the same thing, but we’ll let that slide.)

Then the nerd part of my brain kicked in. I started wondering: is this actually “Copilot” talking to me, or is this just the website scaffolding around it? Is the AI concerned about my well-being, or did some product manager write this line in a Figma file six months ago and ship it as a timed banner?

So, naturally, I asked Copilot about it in a different session. And it answered:

What do YOU think of AI?

Exploring the digital frontier, one prompt at a time

If you’ve been following this blog, you already know I’ve had my share of AI adventures—mostly good, a few chaotic, all interesting. I started out pretty skeptical back in the early ChatGPT days, but somewhere between code generation, design help, blog proofreading, and producing videos for The Pancake Delivery Frog, AI won me over as a genuine time-saver.

It’s helped in the kitchen, in the Google Play Store, and even in building my "personal fitness tracker" web page (which reminds me: I should probably go walk today). And yes, it’s powered some sillier projects too—looking at you, Joe's Land Fishing.

But that’s my AI journey. What about yours? Any AInecdotes you’d like to share with me (and the 1.5 people who read this blog regularly)? Any concerns over "AI's Big Red Button Not Working"? What's one thing AI has helped you with that surprised you? Drop them in the comments!

Wasted Credits and French Frogs: My AI Video Odyssey

It's Arten, the Pancake Delivery Frog!

What's green, hoppy, and delivers delicious golden circles? Why, The Pancake Delivery Frog, of course! Never heard of him (Google search results here)? Well, you should check him out at his channel or, even better, go look at the playlist which includes The Pancake Delivery Theme Song as well as Episode 1 (Pancake Delivery Frog in: The Mayor) and Episode 2 (Pancake Delivery Frog in: The Contraption). Hopefully you'll enjoy the delicious videos (at least the theme song one). But as it turns out, the "making of" story behind these videos is just as much of an experiment as the episodes themselves... so read on for a not‑quite‑excruciating recap of occasionally‑excruciating AI techno‑wizardry.

The Heart of the Matter: Style vs. Life-Saving Stats

Withings Scanwatch on my wrist

This is my Withings ScanWatch, a hybrid “smart” fitness watch. I’ve been wearing the 42mm black version (the original model, not the ScanWatch 2) for a long time now, paired with the metal oyster band, and it’s become part of my everyday routine.

What I love most is the balance it strikes: classic analog style with just enough smart features. The tiny digital display scrolls messages, calls, and notifications, and while you can’t reply from the watch, it’s great for deciding whether something needs immediate attention. The battery life is phenomenal—measured in weeks, not days—and it tracks steps, heart rate, sleep, and offers on‑demand ECG and SpO2 readings. It even does occasional automated SpO2 checks during sleep.

The ECG feature has been genuinely useful. It once captured an episode of afib when I felt palpitations and ran a recording. I sent the PDF to my cardiologist, which led to a follow‑up evaluation. So this watch has absolutely earned its place on my wrist.

But there’s one thing it doesn’t do: continuous heart‑rate monitoring. It only tracks continuously during a manually started workout session. And that’s where my dilemma begins.

Gemini AI is Definitely Smart

I'm building a disc-ingestion script for ripping all my DVDs and Blu-rays to my computer so that we can watch all our videos without having to go find the disc, load it into the XBox, find the XBox remote, try to remember which button is "pause" when we need to get a drink or dispose of a drink we got earlier (i.e., visit one of the throne rooms in the house), etc. I've been using Copilot and Gemini for refining the system (which also pokes Gemini API for some intelligent determination of disc to movie/TV listings). 

I think I have 'Shiny Object Syndrome'

Reaching for that next shiny object

So, I love "new things." (Doesn't everyone?) According to Copilot, here's why it happens (in normal, non-medical terms):

• New ideas feel rewarding and energizing.
• Finishing requires sustained, sometimes boring effort.
• Perfectionism can make the “finish line” feel intimidating.
• Creative minds often generate ideas faster than they can execute them.

I feel that "perfectionism" bit, and another "term" Copilot offered was "Analysis paralysis" - getting stuck in the thinking stage instead of the doing stage - which I think is another thing I suffer from (I find it hard to make decisions sometimes - ok, most of the time). It also suggested "Project hopping" - moving from one idea to another without closing the loop - which seems accurate, too.

AI shortcomings (and some Washington Commanders sideline) - why you shouldn't always trust AI

A story about how AI can go wrong when you expect it to act like a simulation engine

Maybe you know, maybe you don't: I'm a Washington Commanders (née Redskins) fan. Have been for a long time, more than four decades now. Good times (NFL championships/Super Bowls, magical Jayden Daniels rookie season), bad times (Snyder era, Sean Taylor), and just about everything in between. Even when it was hard, I was still a fan. (Note: I'm not old enough to recall the incredible Sammy Baugh as their QB/Safety/Punter - if you're unfamiliar with that name, and an NFL fan, you should definitely go read that article on his incredible fifteen years at Washington.)

To say this season was a disappointment is an understatement. With that in mind, I turned my attention toward the 2026 draft. And that's where I ran into major shortcomings in the AI realm.