Carbon + /swarm in Antigravity: Big Model Thinks, Lighter Models Work
samcharrington · x · 2026-11-12
Sam Charrington's recap thread: Carbon + /swarm in Antigravity hints at Google's direction — a big model does the thinking while many lighter models do the work, forming a hierarchical agent architecture.
Related event: Google Antigravity launches /swarm multi-agent swarm mode(10 posts)→
More from coding & agent
- Stanford NLP course's best homework: build your own agent harness — stanfordnlp · 2026-11-12
- Anthropic details agent memory: dreaming organizes Claude's memory, wiki+search hits 61% — RLanceMartin · 2026-11-12
- Talk preview: scaling 1,000 Fable 5.2 agents to formalize Fermat's Last Theorem — RLanceMartin · 2026-11-12
- Opinion: AI infra is becoming a coding runtime as intelligence units outgrow tokens — prateekj · 2026-11-12
- Claude Docs/Slides block external MCP clients: no public API, export only — steipete · 2026-11-12
- Three AI game dev competitions land this month, one with a $47,800 prize pool — Promptmethus · 2026-11-12