Dots Connected
I build product people actually love and use it. The interesting part was never the model or the infra on its own — it's the loop between what people need and a system reliable enough to benefit them. Right now I'm researching multi-agent for personalized learning at the Beckman Institute, and helping build an AI copilot for aircraft. Before this, I built data infrastructure at Sonic SVM on Solana, and worked on growth and ads at Tencent and Baidu. Looking back, the dots connect: each role taught me a different part of that loop — what people need, how to capture the signal, how to make the system hold in production.
I believe a great tool is a bicycle for the mind that amplifies human intelligence.
Thoughts
Is Alignment all you need in AI-native Team?
Alignment is how people work well together, and how people work with agents too. Just don't micromanage.
You Can't Sell a Skill
Skills and MCP servers solve different problems, and only one of them can be a business
The Shutter Is Proof You Were There
Great photos reach across time to someone who wasn't there
Your Agent's Bug Is Structural, Not Runtime
Most agent failures are structural; fix the structure first
Most Production Features Don't Need an Agent
If a task can't justify 4× the tokens, build a workflow
Nowhere to Go
When there's nowhere to go, the mind surfaces for air
The Simplest Truths
Why Buffett's simplest principles are the hardest to live by
Behind the Build: My Tools & Workflow
Tools matter only when they turn thinking into action
From n to p
When trials are free, the edge is what won't scale
The Zen of A/B Testing
Small-step trial and error compounds into big gains