🚀 a16z: Knowing When to Stop — The Art of Making an AI Loop Converge
a16z partner Yoko Li unpacks "loop engineering" — letting AI agents iterate on their own work until a verifier says stop — and why most loops don't know when to quit.
• In one live test, the first $1.40 of spend took a Lighthouse performance score from 26 to 89 — the next $2.84 (67% of the total bill) bought zero additional points.
• A web-agent benchmark found going from 1 to 10 samples lifted success from 38.8% to 43.2%, but doubling again to 20 samples added just 0.2 points for twice the tokens.
• "The systems that matter will not be the ones that can keep going. They all can," Li writes — the differentiator is deciding in advance what "done" costs.
🔗 Read more
#a16z