Mollick: Claude Projects Spins Up 18 Specialist Agents to Crack Historical Mysteries
emollick · x · 2026-09-18
Ethan Mollick details how Claude Projects handles agent teams: a main orchestrator spawns specialists, mixing expensive and cheap models. He tasked it with famous historical mysteries—it ran 18 parallel threads, each with sub-agents simulating scenarios and breaking codes, then skeptical agents fact-checked the write-ups over a day of work.
Related event: Mollick Tests Claude Projects: Multi-Agent Teams Self-Organize(3 posts)→
More from coding & agent
- Each Perfetto bar maps to one GitHub Actions job; Chrome traces break nesting — DanielLockyer · 2026-11-02
- Google launches Connected Apps Platform: MCP apps inside Search and Gemini — DynamicWebPaige · 2026-11-02
- Visualize GitHub Actions CI timelines with a Perfetto trace file your agent generates — DanielLockyer · 2026-11-02
- Production Incident Investigation: A Six-Step Playbook from Triage to Postmortem — _jaydeepkarale · 2026-11-02
- Google's open-sourced "Elephant-Goldfish" workflow separates planning from review to curb sloppy AI output — gaganghotra_ · 2026-11-02
- InfoQ: A Systemic Approach to Memory, Knowledge, and Context in Agentic AI Architectures — AdiPolak · 2026-11-02