Evan Lowery

Husband | Father | Coach | Meteorologist (Millersville, Plymouth State) | Programmer

[Evan Lowery @EvanLoweryWx]

@godofprompt Claw

[Evan Lowery @EvanLoweryWx]

@BrianRoemmele @grok Fascinating approach

[Evan Lowery @EvanLoweryWx]

@RealFletch17 Beautiful

[Fletch17 @RealFletch17]

WOW this hit hard!
Enjoy every minute!
It goes in a blink
🙏🏻🙏🏻🙏🏻

[Evan Lowery @EvanLoweryWx]

@OfficialLoganK Yes please!

[Linus ✦ Ekenstam @LinusEkenstam]

Gemini 3 has only been out for 18 hours

But people are already creating insane things with it.

Here are my top 13 examples, enjoy

1. 3D Pacman on tiny Planet - by TomLikesRobots

[Carlos E. Perez @IntuitMachine]

I just read a paper that completely broke my brain.

It describes a system that solved an AI task with over 1,000,000 sequential steps... with ZERO errors.

Using AI models that are known to be flaky and make mistakes.

How is that even possible? 🤯

We all know LLMs have an error rate. Even 99.9% accuracy is a death sentence for long tasks.

Imagine you need 1,000 correct steps in a row. With a 99.9% success rate per step, your chance of finishing the whole thing is only ~36%.

At a million steps? Forget it. It's statistically impossible.

So for years, the race has been to build bigger, "smarter" models to get that per-step error rate closer to zero. We're trying to build a perfect genius.

But this paper ("Solving a Million-Step LLM Task with Zero Errors") does the complete opposite. It's a total paradigm shift.

Here's the "holy shit" moment:

Stop trying to make the AI perfect. Instead, build a system that's immune to its imperfections.

How?

Smash the problem into the tiniest possible pieces. (They call it Maximal Agentic Decomposition).

Have a team of simple, cheap AIs vote on the answer for each tiny piece.

It's less like hiring one world-class chef and praying they don't have an off day, and more like designing the McDonald's kitchen.

The system guarantees the burger is the same every time, even if any individual worker could mess up.

The reliability comes from the process, not the person.

They tested this on the Towers of Hanoi puzzle—a classic benchmark where AIs fail spectacularly as the task gets longer.

They set it up for 20 disks. That requires 1,048,575 perfect moves in a row.

(seriously, over a million steps)

A single AI trying this would be a comedy of errors.

But their system of "micro-agents" voting on every single move... nailed it. Flawlessly.

And the plot twist? The most expensive, "state-of-the-art" models weren't even the best for the job. A smaller, cheaper model (gpt-4.1-mini) was more cost-effective because the tasks were so simple.

This is a huge deal for AI safety, too.

A single, god-like AI is a black box. It's unpredictable.

But a system of a million simple agents? You can inspect it. You can audit each step. The agents have no grand "worldview"—their entire existence is to solve one tiny puzzle and then disappear. It's controllable.

So next time you're building something with an LLM, maybe stop asking "how can I prompt the model to be smarter?"

And start asking: "How can I design a system where it's okay for the model to be dumb?"

The real power isn't just in the model. It's in the architecture you build around it.

This isn't just about AI. It's a fundamental lesson in engineering and problem-solving.

You don't always need perfect components to build a perfect machine. You just need a damn good design.

...which makes you wonder what else we're trying to solve by chasing individual perfection instead of building better systems.

[Evan Lowery @EvanLoweryWx]

@IntuitMachine Fascinating

[Evan Lowery @EvanLoweryWx]

@kyleshannon @davidpattersonx Could there be a flood of AI agent companies entering the marketplace that drive prices towards zero? This could then lead to massive unemployment and civil unrest unless the rate of change is so rapid that all prices fall at the same rate (global instantaneous deflation).

[Figure @Figure_robot]

Introducing Figure 03

[Evan Lowery @EvanLoweryWx]

@danfaggella @esaagar We're in Phase 2?

[Evan Lowery @EvanLoweryWx]

@YouTubeTV Don't Drop NBC, Bravo, USA and more! https://t.co/QYvmJmgPMG #GetYourChannels

[Evan Lowery @EvanLoweryWx]

@GrdDscntN2Madnz @RobertMSterling Interesting perspective - likely has an impact. Affordable housing gives young couples the space and freedom to start a family. I'm 46 and most friends are married. A few are single or divorced... I must be on the edge of when this trend changed

[Evan Lowery @EvanLoweryWx]

This is very concerning. Unidata is a critical hub of weather data, open source software, education, and innovation. Many small and large US weather companies and universities rely on their data feeds and technical support. I understand the concept of cutting fat, but this is more like stabbing yourself in the heart. They need to be funded. @elonmusk

[NSF Unidata @unidata]

Due to the current gap in funding from the U.S. National Science Foundation, the NSF Unidata Program is pausing most operations. Nearly all staff will be furloughed until funds from our existing NSF grant become available. For more information, see https://t.co/SDPRZf3bET

[Evan Lowery @EvanLoweryWx]

@IterIntellectus This doesn't look real

[Evan Lowery @EvanLoweryWx]

@martinmbauer Fascinating, thanks for sharing

[Evan Lowery @EvanLoweryWx]

@ryanvivianlive @ExxAlerts Same question. Of course paying less taxes is great, but where will the money come from to replace this?

[Evan Lowery @EvanLoweryWx]

@nickshirleyy Good work Nick, love getting a raw perspective from people on the ground

[Evan Lowery @EvanLoweryWx]

@BugNinza Wow

[Evan Lowery @EvanLoweryWx]

@MatthewBerman Congrats, enjoy your videos