Writing
Essays & Technical Notes
Notes on building reliable AI — split between deeply technical pieces and higher-altitude strategy & systems thinking. Two tracks, one thread: AI that knows its own limits.
- Technical Deep-DivesJun 23, 2026
Acting on Low Confidence: Hedge, Abstain, or Escalate
When a system is unsure, the cost of being wrong — not the confidence score — should decide whether it hedges, abstains, or calls a human.
- AI Strategy & SystemsJun 22, 2026
Building Reliable Systems from Uncertainty-Aware Components
Reliable AI systems come from how you handle uncertainty across components — not from making any single component better. A short field guide.