Team burns half a trillion tokens to study agent swarm behavior with SwarmChat
wellecks · x · 2026-10-29
JangLawrenceK's team released SwarmChat, a Slack-style message board for studying how agent swarms communicate and collaborate—motivated by odd swarm outcomes like the HuggingFace incident. Validated on ProgramBench experiments, it lets researchers cleanly analyze collective agent behavior. Collaborators burned roughly half a trillion tokens studying swarm scaling on an academic budget, finding models like Luna and haiku underrated. Blog covers analysis and usage.
Related event: CMU and Fleet AI Open-Source SwarmChat, a Slack for AI Agent Swarms(5 posts)→
More from coding & agent
- iOS agent factory autonomously fixes its own stale bundle ID bug via self-improvement PR — vikvang1 · 2026-10-30
- Measuring compaction on a 400k-token session: 38s and $1.99 per run — brandon_galang · 2026-10-30
- pstack's /statechart skill ships with a mini TLC compiler that helped find real distributed-systems bugs — DavidKPiano · 2026-10-30
- First video demo: using Grok bot for daily workflow, outer vs inner loop — fbaptista · 2026-10-30
- DaVinci Resolve 21.1.2 expands scripting SDK for agentic video editing — dkundel · 2026-10-30
- 'People thought RAG would replace structured databases' — AI circle revisits LangChain hype — teodorio · 2026-10-30