Why Do ChatGPT's Multi-Agent Modes Use the Same Model Size for Every Agent?
flowersslop · x · 2026-10-20
Developer flowersslop questions why ChatGPT's ultra multi-agent modes run the same model size for every agent, calling it wildly inefficient. He proposes a model hierarchy — a big 'Astra' boss spawning 'Sol' agents, which spawn smaller 'Luna' agents for simpler tasks — arguing that allocating compute by task complexity would make far more sense.
More from coding & agent
- ClaudeST: an open-source native Claude client for Atari ST retro computers — Hakan_Ozalp · 2026-10-20
- OpenCode: the open-source Claude Code rival that runs GPT, Gemini or local models — thisdudelikesAI · 2026-10-20
- DevDay demo uses Decisions API to detect tool use inside live voice conversations — gabrielchua · 2026-10-20
- GPT Live + Decisions API powers fully voice-driven slide demo at OpenAI DevDay — gabrielchua · 2026-10-20
- Decisions API integration with Live API showcased as fast GPT backend in demo — gabrielchua · 2026-10-20
- DoorDash runs 130K automated tasks a month: inside 8 AI software factories — Pavan_Belagatti · 2026-10-20