Agent harness and loop engineering are reshaping model optimization

AI researcher Elvis Saravia discussed the evolution of agent engineering, from the problem of telling agents when to stop to the rise of loop engineering, arguing that the Codex agent's harness in turn determines how models get optimized.

2026-09-30 ~ 2026-09-30 · 2 related posts

• Key notes from a talk on the Codex agent and how harnesses shape model optimization — omarsar0 · 2026-09-30
• From 'when to stop' to loop engineering: agent harnesses shape model training — omarsar0 · 2026-09-30