Multiplayer AI
Funny how we standardized on the word "harness" to describe the environment in which agents are executed and the human/agent interface associated with it. The word harness suggests a handle for humans to box and control agents to exploit their power. But when intelligence sits on both ends of the interface, it is no longer a one-way handle but rather a bi-directional medium. Maybe the cold truth is that the harness is probably as much for us as it is for agents[0]! Purposefully or not, a harness is also inherently a single-player concept. 3 years ago I wrote[1]: ChatGPT is the Pong of LLMs. Next we'll inevitably go through a trough of disillusionment… … but imagine, one day we'll get the DOOM, Civ, Red Alert, and Counter Strike of LLMs🤩 Let alone multiplayer modes🔥 Continuing with that analogy… With Dust, we're building something like the level editor for Pong… whatever that means🤔 Now that gets me thinking about multiplayer mode 😬 I would concede that with the emergence of agents
Multiplayer AI ← HOME March 26, 2026 Multiplayer AI Funny how we standardized on the word "harness" to describe the environment in which agents are executed and the human/agent interface associated with it. The word harness suggests a handle for humans to box and control agents to exploit their power. But when intelligence sits on both ends of the interface, it is no longer a one-way handle but rather a bi-directional medium. Maybe the cold truth is that the harness is probably as much for us as it is for agents[ 0 ]! Purposefully or not, a harness is also inherently a single-player conce
Explore this link on the map →related reading
- Interaction Models: A Scalable Approach to Human-AI Collaboration - Thinking Machines Labthinkingmachines.ai
- Scaling Managed Agents: Decoupling the brain from the hands \ Anthropicanthropic.com
- One Developer, Two Dozen Agents, Zero Alignmentmaggieappleton.com
- Arjun Virkarjunvirk.com
- [2411.00114] Project Sid: Many-agent simulations toward AI civilizationarxiv.org
- Building Effective AI Agents \ Anthropicanthropic.com
- [2606.09498] Self-Harness: Harnesses That Improve Themselvesarxiv.org
- Building Effective AI Agents \ Anthropicanthropic.com
- Real-Time Strategy games and AI interfaces - by David Hoangproofofconcept.pub
- Towards self-driving codebases · Cursorcursor.com
- Don’t Build Multi-Agents | Cognitioncognition.ai
- Effective harnesses for long-running agents \ Anthropicanthropic.com