Intents × AI = Silicon species
I am Yong Wang — a builder, and CTO at an AI fintech startup in Dublin. Days go into AI agent architecture, harness engineering, product engineering and running a team. Evenings go into building side projects, writing, and thinking.Recent
DeepSeek just open-sourced its Harness and, together with Peking University, released a paper that looks past the model itself and tackles a foundational problem for the next generation of agents:Can Agents Safely Rewrite Themselves?- When agents can be highly customized and continuously self-optimize, they become a company’s real moat.When agents can be highly customized and continuously self-optimize, they become a company
This site. Every string is authored in both languages at once, so a half-translated page is a type error rather than a discovery.intentplex- Some principles for building consumer AI products:Some principles for building consumer AI products:
- “What’s your team’s competitive advantage if agents can do everything?”“What’s your team’s competitive advantage if agents can do everything?”
- If you doubt the power of philosophy, try this: take a piece of AI-generated text and ask an AI to perform an adversarial review of it through the lens of Aristotle’s final cause—in other words, examine whether the text actually fulfills t…If you doubt the power of philosophy, try this: take a piece of AI-generated text and ask
- With AI, when building an app, you should spend 60% of your time building and running its marketing system. Otherwise, overall, you’re doing it wrong.With AI, when building an app, you should spend 60% of your time building and running its
Imagine every worker ant in a colony suddenly became 4x more productive.Imagine every worker ant in a colony suddenly became 4x more productive
© 2026 Yong Wang