MIT AI Risk Repository · Risk Sub-Category · 63.06.03

Undesirable Capabilities

Category: Selection Pressures

Description

"Undesirable Capabilities. As agents interact, they iteratively exploit each other’s weaknesses, forc- ing them to address these weaknesses and gain new capabilities. This co-adaptation between agents can quickly lead to emergent self-supervised autocurricula (where agents create their own challenges, driving open-ended skill acquisition through interaction), generating agents with ever-more sophisticated strate- gies in order to out-compete each other (Leibo et al., 2019). This effect is so powerful that harnessing it has been critical to the success of superhuman systems, such as the use of

From Multi-Agent Risks from Advanced AI (Hammond2025), as extracted by the MIT AI Risk Repository (CC BY 4.0).

Classification

Causal entity
AI

Subdomain definition: Risks from multi-agent interactions, due to incentives (which can lead to conflict or collusion) and/or the structure of multi-agent systems, which can create cascading failures, selection pressures, new security vulnerabilities, and a lack of shared information and trust.

How other frameworks describe this risk

Other entries from Hammond2025