Interpretability
What models reveal, hide, compress, and "think" beneath the answer.
AI is moving from tools we prompt to systems that plan, delegate, verify, and act. These essays examine what that shift asks of software, companies, labor, and human judgment.
Intelligence is becoming abundant. Trust, context, taste, accountability, and agency are becoming the scarce things.
What models reveal, hide, compress, and "think" beneath the answer.
How agentic systems stay bounded, useful, honest, and accountable in messy real environments.
How AI changes work, institutions, markets, education, and power.
Agents, enterprise infrastructure, cyber risk, autonomy, and self-improving workflows.

The next great companies will turn abundant intelligence into capability people can actually own.

General intelligence is lowering the cost of attack and putting machine-speed defense within reach.

AI alignment is only half the problem. The critical thinking we are offloading is the very faculty alignment depends on.

AI infrastructure is pushing compute toward orbit. The sun never sets there, but the heat still has to go somewhere.
The next internet will be built for agents discovering, verifying, negotiating, and acting on our behalf. The real test is whether we design that infrastructure with open protocols, accountable identity, and human agency at the center.