Model-Agent Flywheel

The flywheel spins fastest where one player holds both ends (Anthropic + Claude Code): the model knows how Harness will call it, Harness knows the model’s boundaries.

Experiment: without changing the model, only changing Harness, accuracy increased from 52.8% to 66.5% – Harness’s leverage is high precisely because the model hasn’t reached this point yet.

The flywheel is the deepest moat of the era.

For model builders – spin real-world scenarios back into training.
For application developers – Harness is a sharp lever in the short term, but the durable moat is beyond technology: exclusive data, channels, user trust, network effects.

The three questions “what it sees, what it can do, how to verify” will not become obsolete.