Berkeley study: the right agent harness cuts cost of the same result by 71%
MartinGTobias · x · 2026-09-18
A new Berkeley study shows that harnesses—the systems orchestrating AI agents—effectively set the price of an answer: the right harness cuts the cost of achieving the same result by 71% with no loss of accuracy.
VC ttunguz frames this as the "Harness Margin Opportunity": the better the harness, the better the business. Vertical agents, he argues, are essentially just better harnesses—meaning engineering quality at the orchestration layer translates directly into margin.
More from coding & agent
- Experimental Jev-powered RLS linter catches Supabase policy bugs rule-based lint can't — SeanOliver · 2026-09-19
- Virtual green screen from a RealSense D436: depth-based RGB filtering, no backdrop needed — chrismatthieu · 2026-09-19
- Runway MCP turns video to 120fps with a single prompt — tlakomy · 2026-09-19
- Cost breakdown: 100 LLM calls in 8.5 seconds for roughly a quarter of a cent — narphorium · 2026-09-19
- Dev builds an interpreter for an English logic language so an LLM can reason via proof search — narphorium · 2026-09-19
- AgenticLinux Ships an Immutable Distro Preloaded With Claude, Codex and Docker Sandboxes for Agents — steipete · 2026-09-19