Are Harnesses Worth the Cost?

T2Covered by 1 source · first reported by Martin Fowler / Overreacted / Kent C. Dodds / Josh Comeau at 13 Oct, 13:35 UTC

Naresh Jain compares coding agents building the same API service with and without a behavioral harness. A frontier model, GPT-6 Sol, passed every external evaluation either way. But a cost-optimized model, GPT-6 Luna, succeeded in only 3 of 10 unharnessed runs and all 10 with the harness. While…

dev

Sources

• T2Are Harnesses Worth the Cost?Martin Fowler / Overreacted / Kent C. Dodds / Josh Comeau13 Oct, 13:35