Not every model knows how to lead: GPT-5.6 and Opus 4.8 delegate well, smaller models don't
nouhadziri · x · 2026-10-14
New results from the multi-agent team experiments show not every model can lead a team:
- GPT-5.6 and Claude Opus 4.8 delegate and gain from it
- Claude Opus 4.7 barely delegates
- Claude Haiku 4.5 and Gemini 3.7 Flash delegate a lot but gain nothing
For a team to help, two things must go right: the lead must choose to delegate, and it must make good use of what comes back. The authors argue leading is a trainable skill — the focus of their next work.
Related event: Study on scaling coding agent teams: placement matters more than headcount(14 posts)→
More from coding & agent
- Dev's honest scoreboard: pattern rules catch under 25% of prompt injections, guard model catches most — colinmcnamara · 2026-10-15
- SpaceX's Cursor acquisition hailed as one of the fastest, best-executed integrations — kieranklaassen · 2026-10-15
- cantrell on Gemini 4 Argon: heavy thinker, building long decode to push past 64K token limit — cantrell · 2026-10-15
- Creator Shares Fix for AI Video Voice Consistency, Compares Claude vs ChatGPT vs Figma Make — Tegadesigns · 2026-10-15
- Indie dev builds AI game in 4 days: 297 Magnific assets, one-prompt Meshy animations — techhalla · 2026-10-15
- Google's AIS Team Hiring FTEs and Interns for AI-Infra Agents and Verifiable Reasoning — VioletNPeng · 2026-10-15