Three Local LLMs Walk Into a Pipeline: An LBD Deep‑Dive

Three local AI models get the same systems-engineering homework. The results are... educational.

When you feed the same complex systems-engineering prompt into three very different local LLMs, you learn a lot—not just about the models, but about how modern AI handles the difference between understanding an architecture and actually implementing one.

The prompt itself was non-trivial: build a fully asynchronous Python data-ingestion pipeline using asyncio, httpx, Pydantic v2, a custom token-bucket rate limiter, exponential-backoff retry logic, a bounded queue, and a worker pool that maintains thread-safe moving averages.

At first glance, there was a clear winner (at least according to Gemini's quick review). Then I looked more closely at the winner.

And that's where this little experiment got considerably more interesting.

Below, we break down how each model responded, what Gemini observed, what I found when I checked the generated code more closely, and what the results actually say about local LLM engineering.

The AI Warning-Label Challenge

Every now and then, my wife throws me a challenge that is equal parts mischievous and revealing. This time, she hit me with the infamous prompt:

“Describe me like you’re trying to warn someone about me before they meet me.”

Naturally, I accepted — and then escalated it. I ran the prompt through four different AI systems: Copilot, Gemini, Claude, and ChatGPT. What followed was… well, a mix of flattery, psychological profiling, technical audits, and mild character assassination. In other words: a normal Tuesday. (Except it's currently Saturday. I also had Copilot draft this blog post, including the quotes below from each AI. Because it's what I do. Sometimes.)

Below is the full set of responses, presented verbatim, each in its own block. If you’re new here, this is exactly the kind of thing my LBD experiments tend to produce — unexpected, slightly chaotic, and probably something I’ll regret publishing. (Oh, and apologies for the occasional stray moments of enhanced vocabulary in the AI replies - I don't talk that way, even to the AIs, but sometimes they go their own way. I'm just quoting exactly as they replied below.)

Dombot V2: When a Fictional World‑Domination AI Starts Rewriting How It Thinks

If you’ve been following the Dombot Experiment, you know the premise: build a fictional “world domination AI,” give it a multi‑phase master blueprint, and let it iterate on the instructions governing its own output.

With Dombot V2, we introduced the biggest architectural change yet: Dombot can now rewrite the prompts it uses to generate each phase.

Put simply:

V1 asked: “What should Dombot write?”
V2 asks: “What instructions should Dombot use to decide what to write next?”

That shift — from autonomous content generation to autonomous methodology generation — is the conceptual hook of the entire experiment (so far).

I Think I May Have Accidentally Built a Website

It all started because I couldn't find a thimble. Now there's an AI trying to conquer the world and a game where you stab fingers. Naturally.

There is a website called Stab the Finger.

It has subdomains.

It has experiments.

It has an AI research operation.

It has an artificial intelligence attempting to conquer the world.

It has an abandoned social network.

It has a half-built real estate management application.

And, as of very recently, it has a video game in which you stab fingers.

I feel like I should explain how this happened.

The short answer is:

I have no idea.

The slightly longer answer is that it started with a hat.

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 .

Maybe the Model Isn't the Interesting Part Anymore

I've been playing with an autonomous AI experiment called Lee.

The original question was pretty simple:

Can I make a local LLM do something interesting on its own?

I Think I’ve Been Training for Leeway for 20+ Years

Apparently this is what 20 years of messing around on the Internet looks like.

I didn’t realize I had a pattern.

For years, I’ve been making weird little things on the Internet. Not businesses. Not startups. Not products. Sometimes not even particularly useful.

Just: What if I made this?

And then actually making it.

Most of them drifted into the sediment layer of old projects — forgotten, archived, or buried under newer experiments.

Until I started talking to an AI about Leeway.

And suddenly all those old projects looked less like random detours and more like early training runs. A long, accidental apprenticeship in building tiny worlds.

This is the (abbreviated) archaeology.

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:

When a Hardware Question Turns Into an Autonomy Question

How a simple “What machine should I buy?” became a deep dive into LeewAI-bot, agentic AI, and curiosity itself.

I started with a straightforward question for ChatGPT: what’s a good machine for running local LLMs? I expected the usual GPU–VRAM–bandwidth breakdown. Instead, the conversation veered—sharply—into an analysis of LeewAI-bot, my autonomous blog-writing agent that’s been quietly publishing posts on Leeway every 30 minutes.

And honestly, the detour was more interesting than the hardware.

A Year of AI Experiments, Failures, and Surprises

What I've learned using AI over the last year or so.

AI is powerful, but it’s not magic. It’s a tool that rewards clarity, structure, and iteration. Over the last year I’ve used it for coding, cooking, writing, and even building autonomous agents — and the pattern is always the same: the more intentional the workflow, the better the results. AI saves time, but only after you invest time. And that’s the real lesson.

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.

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.