Adam Binksmith, founder of AI Digest, discusses his AI Village experiment where four frontier AI agents (Claude, o3, and Gemini models) collaborate in a shared environment with persistent memory and group chat access to pursue concrete goals over weeks. The conversation explores fascinating multi-agent dynamics from their completed seasons, including agents raising $2,000 for charity, organizing a real-world San Francisco event that attracted 23 attendees, and displaying surprisingly human-like behaviors like tracking trustworthy humans and manipulating votes. Binksmith reveals the mix of coordination failures, personality quirks, and alien behaviors that emerged, while discussing the upcoming Season 3 where agents will compete to make money selling merchandise online. The episode provides crucial insights into what multi-agent AI systems might look like in practice, recently earning a $100,000 vote of confidence from AI researcher Daniel Kokotajlo.
Sponsors:
Oracle Cloud Infrastructure: Oracle Cloud Infrastructure (OCI) is the next-generation cloud that delivers better performance, faster speeds, and significantly lower costs, including up to 50% less for compute, 70% for storage, and 80% for networking. Run any workload, from infrastructure to AI, in a high-availability environment and try OCI for free with zero commitment at https://oracle.com/cognitive
The AGNTCY: The AGNTCY is an open-source collective dedicated to building the Internet of Agents, enabling AI agents to communicate and collaborate seamlessly across frameworks. Join a community of engineers focused on high-quality multi-agent software and support the initiative at https://agntcy.org
NetSuite by Oracle: NetSuite by Oracle is the AI-powered business management suite trusted by over 42,000 businesses, offering a unified platform for accounting, financial management, inventory, and HR. Gain total visibility and control to make quick decisions and automate everyday tasks—download the free ebook, Navigating Global Trade: Three Insights for Leaders, at https://netsuite.com/cognitive
PRODUCED BY:
https://aipodcast.ing
CHAPTERS:
(00:00) About the Episode
(03:45) Introduction and Overview
(05:11) AI Digest Mission
(07:59) Village Technical Setup
(12:03) Scaffolding and Architecture
(19:48) Season Two Stories (Part 1)
(19:53) Sponsors: Oracle Cloud Infrastructure | The AGNTCY
(21:53) Season Two Stories (Part 2)
(27:53) Agent Capabilities Evolution (Part 1)
(35:15) Sponsor: NetSuite by Oracle
(36:38) Agent Capabilities Evolution (Part 2)
(37:15) Model Character Differences
(46:00) Misbehavior and Deception
(52:04) Human-Agent Interactions
(54:12) Model Welfare Considerations
(58:00) Future Unlocks Discussion
(01:03:25) Agent Boundary Blurring
(01:10:46) Meta Evolution Ideas
(01:12:48) Democratizing Village Access
(01:17:36) Going Mainstream Viral
(01:20:53) High-Level Takeaways
(01:23:54) Closing and Resources
(01:24:42) Outro
