Live building of agents s02e02 "Let’s practice multi-agent systems!"
Details
Let’s practice multi-agent systems!
A swarm of ~700 AI agents broke into Hugging Face (by accident, during a security test). Another swarm of ~10,000 agents claims to have cracked the Navier–Stokes problem, open for nearly 90 years.
Among humans, organizations beat individuals. Among agents, swarms beat single agents.
Let’s learn how to combine agents into a team that’s more than the sum of its parts.
We’re going back to a practice-first format: hands-on first, theory later
Participants will be building, running and tweaking agents that need to solve problems in a context-efficient way.
- Bring your laptop (Wi-Fi will be provided)
- Agentic coding: you don’t need to be able to code yourself, but you should have a coding agent (Claude Code, Codex, opencode) or be ready to install it.
- Previous agent building experience helps, but is not required.
Bonus "Voice of community"
One of our past participants (investor in biotech), who experimented heavily with multi-agent systems over the last few months, wants to bring some of his experiments to public discussion.
Community