Agent Reliability: Your Harness Is the Product
Why long-running agents fail, and the verification loops that keep them honest.
Coming soon
SIGNALS
Research, investment, and the weekly signal
Deep dives on verification and reliability, plus where capital actually meets constraint.
Building an agent harness from scratch. Build log #1
Watch →Jun 2026
Can AI Judge AI?
What LLM-as-judge gets right, where it quietly fails, and how to calibrate it before you trust it.
Ranking Bottlenecks for AI Infra Investment
A framework for where the real constraints sit: compute, data, energy, or trust.
We Are as Gods, and what we lost when we stopped being awed
Watch →Mar 2026
Evals in the wild: a field guide
Watch →Feb 2026
Infra Signal Tracker
A living dashboard of AI infra signals: capex, capacity, and constraint moves that matter.
Auto-compiled weekly. Verified by hand before it ships.
Signal Garden
THE WEEKLY SIGNALNotes on AI, growth, and humanity. Every week.