Ai

Alignment as a runtime surface, policy enforcement without retraining. Team practices that ship.

Model outputs are hypotheses that need verification pipelines to catch errors before users do.

Memory and hands for the model: retrieval that doesn’t hallucinate. Tools that don’t break production.

The physics of production AI: latency engineering that keeps humans in the loop. Token economics that don’t bankrupt you.

Before you build: the mental models for human-AI collaboration. Why L1 copilots need different infrastructure than L4 autonomous agents.

A 6-part series on building production AI systems. The foundation model is the CPU; your product is the computer you build around it.