Why I'm Building AI Education for Kids

JLJeff Liu··2 min read
Why I'm Building AI Education for Kids

I didn’t think I’d hear back from Runway after months passed.

This morning, I got accepted into their Builders program.

I’m incredibly grateful, not just for the tools, which let me apply creative problem-solving, but because it means an institution believes in what I’m building toward - AI education for kids, so no one gets left behind.

I chose this for a reason that isn’t strategic. It’s personal. And it goes back further than I usually talk about.

When I was a kid, my parents were immigrants working every hour they had to get established. So some days I’d wait a long while after school for a ride home.

So I’d wait. And in that waiting, I taught myself to stay curious and keep my own company, which turned out to be the most useful habit I ever picked up.

That habit stuck. It carried me through high school and college, and into graduating around 2008 with no clear map, when I figured the fastest way forward was to build my own.

Wikipedia was where my curiosity went to find the what, the how, the when, and the why, because the books were already dated by the time they reached us. That’s where continuous learning stopped being something I did on the side and became the thing everything else is built on.

The same patterns exist today.

I spent my career in programmatic AdTech and FinTech, industries that ran on AI long before it was a headline. I know what this technology actually does, and I can already see the gap between the people who understand it and the people who don’t starting to widen.

Kids today are inheriting a world being reshaped by AI, and most of what they hear about it is fear. What it takes. Who it replaces. Why to be afraid.

It’s on every feed they scroll.

So I’m building the opposite of fear - a way for kids to get their hands on these tools and see what they can actually make with them. That’s the version I wish someone had handed me while I was waiting, and it’s the one I want to hand the next kid.

Keep reading

Building a Commit Guard for AI Agents That an Adversary Can't Slip Past

I gave a coding agent a guard that checks every commit lands in the repo and branch I intend. My 417 tests were all green. Then I hired a second agent to break it, and it walked through two holes the green suite never thought to check.

Read

Graph Engineering Makes Agent Failure Legible, Not Agents Reliable

A video making the rounds argues graph engineering supersedes the loop-based agent pattern. After building multi-agent systems, I think the loop-versus-graph framing asks the wrong question. Topology decides whether you can SEE a failure, not whether one happens. Reliability lives in the deterministic checks at the edges, not in how you wire the agents.

Read

Claude Desktop vs Cowork vs Code: A Beginner's Roadmap to Which One to Use

Claude Desktop, Cowork, and Code look interchangeable. The real difference is what survives when the session ends, and that decides which one to build in.

Read

Remote-Controlling AI Coding Agents From Your Phone: What's Real, What It Costs, and Where It's Going

For fifty years, controlling a computer meant sitting at it. AI coding agents broke that. Here''s how I drive my agents from my phone, what it actually costs, the local-vs-cloud distinction, and why this turns you from an operator into a conductor.

Read

Running Multiple AI Coding Agents in Parallel: A System for Safe, Self-Merging PRs

Running several AI coding agents on the same repo turns into a coordination problem fast. Here's the system I built to keep them isolated, review each other's work, and merge their own pull requests safely.

Read

AI Native, Human First

You can outsource thinking and execution to AI. But you cannot outsource understanding. Real learning and proactive groundwork are first-class survival skills in the AI era.

Read

Using AI Without Losing Your Humanity

Everyone has access to the same AI tools now. So what sets you apart is no longer how much content you can generate. It's whether it makes people feel something, and whether you can use AI without losing your humanity.

Read

How I Built a Publishing Stack for AI Search

People are finding things through ChatGPT and Perplexity instead of Google. I built a pipeline that handles the optimization for that automatically. Here's how it works.

Read

Building Systems, Then 10x the Output

At Zeta Global, my team gave me room to figure things out. I tried to do the same for the people who came after me, from responsive templates to training engineers across time zones.

Read

45 Rule Files Were Making My AI Worse

I had 45 rule files telling my AI how to behave. The output was getting worse, not better. Then I measured. 170KB of context loaded per session. Here's what happened when I deleted half of them.

Read

Why I Let AI Fight With Itself Before I Ship Anything

When I build with one AI for too long, the output starts drifting, confident but incomplete. A second model catches what the first one misses. Here's the two-pass process I use now.

Read

How I Turned My AI's Mistakes Into Guardrails

I added Husky because of an anti-pattern. CI because of an anti-pattern. PR requirements because of an anti-pattern. None of it came from reading best practices. It came from breaking things and writing it down.

Read