Concern 260 · Working draft · editorial review in progress
Adversarial equilibria
Adversarial equilibria are stable patterns of interaction in which agents keep choosing actions that sustain a harmful conflict.
Understanding the concern
An equilibrium is a situation where changing strategy alone may not help a participant. Agents can become locked into retaliation, resource competition, or mutual obstruction even when all parties would prefer a better arrangement. Local incentives can keep the bad pattern going.
This differs from a temporary disagreement or an accidental collision. The concern is a self-reinforcing strategic pattern. Clear rules, communication, and ways to make credible commitments may help, but their effectiveness depends on the setting and what each agent is rewarded for.
An example
Two automated schedulers repeatedly reserve extra capacity to protect themselves, leaving both organizations with wasted resources.
Illustrative unless identified as a documented case.
Words in plain English
- Agent
- An AI system that can choose and carry out several steps toward a goal, using the tools and access people give it.
- Adversarial
- In this context, designed to challenge, trick, or attack a system.
Evidence and its limits
The report classifies conflict and commitment problems; the scheduling example is a hypothetical mechanism, not a documented incident.
Hammond and colleagues · Cooperative AI Foundation 2025 · Research risk framework
Multi-Agent Risks from Advanced AI ↗ (opens in a new tab)Distinguishes miscoordination, conflict and collusion with examples and research; proposed scenarios are not all observed incidents.
Broader frameworks and background
These resources provide context. They do not establish every claim in this concern.
A question to discuss
What makes the harmful pattern stable, and what coordinated change could make a better outcome possible?
Keep track of different views, what needs checking, and any next step in your own discussion notes.
Open discussion notes →Principles for the conversation
Before you finish · reflect together
Virtues and principles to consider
Virtues are qualities we practice in how we treat people and make choices. They are not scores for judging someone. Use these ideas to explore what a thoughtful response could look like.
Prudence
Prudence means using careful judgment before and during action. It balances worthwhile opportunities with the need to avoid harm that could have been anticipated.
Start with a limited trial, set stopping points, and prefer choices that can be undone when uncertainty is high. Review what happens rather than assuming the original plan remains sound.
Ask together: What is a careful next step, and when should we stop or change course?
Humility
Humility means recognizing the limits of our knowledge and being willing to learn from others. Expertise can be valuable without answering every question.
State where evidence is weak, invite criticism, and listen to people with different experience. Leave room to revise a decision when new information appears.
Ask together: What might we be missing, and who could help us see it?
Stewardship
Stewardship means caring for resources and systems that others depend on, including people who will use them later. It looks beyond the benefit of a quick launch.
Plan for maintenance, energy use, data protection, and eventual shutdown. Ask who will look after the tool when the original team moves on and how future users can avoid inheriting hidden costs.
Ask together: What are we responsible for caring for over time?
Editorial ratings
These are editorial judgments from the register, not measured probabilities or predictions about your situation.
About the register and scoring →More ways to explore
Search for more writing
For more specific or recent material, open a search below or ask for a web summary. AI-generated summaries can contain mistakes; open the original articles to check them.