llm-council built into Hermes: multiple models answer, blind-rank, and a chairman decides
Scobleizer · x · 2026-11-16
Inspired by Karpathy's llm-council, someone built the pattern into Hermes: each model gets its own role, models blind-rank each other's answers, and a chairman picks the final call. It costs a few model calls per run with an upfront cost estimate — suited for decisions you keep going back and forth on.
More from coding & agent
- Three practical tips for getting more out of Fable 5.2, from permission-giving to orchestrating Opus 5.5 agents — dreamwieber · 2026-11-16
- Quant researcher co-writes a short math-heavy book on agentic engineering with LLMs — blaizedsouza · 2026-11-16
- Grok Build v1.0.87 improves multi-agent workflows, MCP panel and session search — XFreeze · 2026-11-16
- Dynamic tool discovery vs loading every MCP schema upfront for agents — Pakiya09 · 2026-11-16
- Swarm orchestration runs 12 parallel agents to build a Blender 3D model, claims tester — venturetwins · 2026-11-16
- AgentWeb lands YC W27 spot building endpoints that let AI agents operate any site — damnGruz · 2026-11-16