From 'when to stop' to loop engineering: agent harnesses shape model training
omarsar0 · x · 2026-09-30
Elvis Saravia traces the evolution of agent engineering: the early problem was telling the agent when to stop, then came "loop engineering." He highlights the Codex agent and harness, noting that harnesses inform how the models themselves are optimized — making harness design a core lever of agent capability.
Related event: Effort Scaling and Agent Orchestration: A New Lever for Multi-Agent Scale(12 posts)→
More from coding & agent
- Google Research open-sources PaperOrchestra, a multi-agent framework for writing AI papers — google-research · 2026-11-16
- ffmpeg-skill gives coding agents local video editing via 42 FFmpeg tools and MCP — kajisho5 · 2026-11-16
- Every's Frontier team on Claude Fable 5.2: overnight agent jobs, cost tradeoffs, real builds — every · 2026-11-16
- Agents Now Reply to Slack Messages on Their Own, Resolving a Prod Incident Ghost-to-Ghost — iamrobotbear · 2026-11-16
- Engineer's Interview Prep Method: Use Claude to Find Which Answers Undersell Your AI Work — brandon_galang · 2026-11-16
- DeepSeek open-sources its app frontend "chat-demo", already at 3.9k stars — NielsRogge · 2026-11-16