Summary

Agents might fail to peacefully trade in high-stakes negotiations. Such bargaining failures can have catastrophic consequences, including great power conflicts, and AI flash wars. This post is a distillation of DiGiovanni et al. (2024) (DCM), whose central result is that agents that are sufficiently transparent to each other have individual incentives to avoid catastrophic bargaining failures. More precisely, DCM constructs strategies that are plausibly individually incentivized, and, if adopted by all, guarantee each player no less than their least preferred trade outcome. Figure 0 below illustrates this.

Figure 0: Payoff space representation of a bargaining scenario. Horizontal (vertical) coordinate: payoff to the first (second) agent. In this toy scenario, two agents can either trade (outcomes on the thick black segment) or wage a costly war (red point). Although going to war hurts everyone, each player might want to accept the risk of war to improve their bargaining position. However, we’ll show how to construct individually incentivized strategies that, if adopted by both, can guarantee each player is no worse off than under their least preferred trade outcome (star).

This result is significant because artificial general intelligences (AGIs) might (i) be involved in high-stakes negotiations, (ii) be designed with the capabilities required for the type of strategy we’ll present, and (iii) bargain poorly by default (since bargaining competence isn’t necessarily a direct corollary of intelligence-relevant capabilities).

Introduction

Early AGIs might fail to make compatible demands with each other in high-stakes negotiations (we call this a “bargaining failure”). Bargaining failures can have catastrophic consequences, including great power conflicts, or AI triggering a flash war. More generally, a “bargaining problem” is when multiple agents need to determine how to divide value among themselves.

Early AGIs might possess insufficient bargaining skills because intelligence-relevant capabilities don’t necessarily imply these skills: For instance, being skilled at avoiding bargaining failures might not be necessary for taking over. Another problem is that there might be no single rational way to act in a given multi-agent interaction. Even arbitrarily capable agents might have different priors, or different approa...

Safe Pareto Improvements

Safe Pareto Improvements