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 Orchestrating Multi-Agent Teams(2 posts)→
More from coding & agent
- Claude Code 2.1.275 release imminent — ClaudeCodeLog · 2026-09-18
- Legora's take: there is no best model — lawyers write evals and Legora BAR picks the winner — soleio · 2026-09-18
- Research with Agents: reflections and lessons from using AI agents in scientific work — _xiang_chen_ · 2026-09-18
- Addy Osmani: Running Agents in Old Codebases — Brownfield Agentic Engineering — rseroter · 2026-09-18
- Google's Stellar Colosseum: many-agent harness proves new math theorems — IgorCarron · 2026-09-18
- Official MCP extension lets agents discover and load Skills directly from MCP servers — solyarisoftware · 2026-09-18