How can humanity survive a multipolar AGI scenario?

My current best guess: Subsidiarity

I've been thinking along these lines for the past few years, but I feel like my thinking was clarified and boosted by Allison's recent series: Gaming the Future [LW · GW]

The gist of the idea is to create clever systems of decentralized control and voluntary interaction which can still manage to coordinate on difficult risky tasks (such as enforcing defensive laws against weapons of mass destruction). Such systems could shift humanity out of the Pareto suboptimal lose-lose traps and races we are stuck in. Win-win solutions to our biggest current problems seem possible, and coordination seems like the biggest blocker.

I am hopeful that one of the things we can do with just-before-the-brink AI will be to accelerate the design and deployment of such voluntary coordination contracts.

I think a lot of thinking around multipolar scenarios suffers from heuristic "solution in the shape of the problem", i.e. "multipolar scenario is when we have kinda aligned AI, but still die due to coordination failures, therefore, solution for multipolar scenarios should be about coordination".

I think the correct solution is to leverage available superintelligence in nice unilateral way:

1. D/acc - use superintelligence to put as much defence as you can, starting from formal software verification and ending in spreading biodefence nanotech;
2. Running away - if you set up Moon/Mars/Jovian colony of nanotech-upgraded humans/uploads and pour available resources into defence, even if Earth explodes, humanity as a species survives. 

Here's what Claude 3.5 Sonnet said in response to this prompt:

Me:

What are the best plans for preventing catastrophes such as everyone dying or a totalitarian government taking over in multipolar AGI scenarios, i.e., ones in which AGI's are aligned to what their human users want to do, and at least one human user order them to do bad things?

Claude:

Let me share some thoughts on AGI governance and safety in multipolar scenarios, while noting this is a complex topic that reasonable people disagree on:

A key challenge in multipolar scenarios is that even if individual AI systems are aligned with their users' values and intentions, some users may have harmful goals. Some potential approaches to address this include:

1. International coordination and governance frameworks that place limits on allowable AI system capabilities and uses, similar to arms control treaties. However, enforcement would be challenging.
2. Technical measures like capability limitations built into AI systems' training that prevent them from being used for certain catastrophic actions, regardless of user intent. The challenge is defining and implementing such limitations without preventing beneficial uses.
3. Focused work on improving human values and cooperation through better institutions, education, and mechanisms for resolving conflicts peacefully. This could reduce the likelihood of actors wanting to cause catastrophic harm.
4. Developing AI systems with some form of common good or humanitarian principles that apply regardless of user instructions, though this involves difficult philosophical and technical questions about how to define and implement such principles.

What are your thoughts on which approaches seem most promising or practical? I'm particularly curious about your perspective on the balance between technical and social/institutional solutions.

___________________________________

I would add to this Defensive acceleration (d/acc) described by Vitalik Buterin (https://vitalik.eth.limo/general/2025/01/05/dacc2.html and https://vitalik.eth.limo/general/2023/11/27/techno_optimism.html).