Open Questions in Creating Safe Open-ended AI: Tensions Between Control and Creativity

TL;DR

This paper explores the safety challenges of open-ended AI systems, emphasizing the tension between their creative potential and the need for control, and proposes research directions to address these issues.

Contribution

It highlights the unique safety concerns of open-ended search in AI and suggests concrete research questions to improve control and safety in such systems.

Findings

Open-ended AI systems pose distinct safety challenges.

Control of creativity in open-ended systems is complex and requires new approaches.

The paper proposes specific research questions to enhance safety in open-ended search.

Abstract

Artificial life originated and has long studied the topic of open-ended evolution, which seeks the principles underlying artificial systems that innovate continually, inspired by biological evolution. Recently, interest has grown within the broader field of AI in a generalization of open-ended evolution, here called open-ended search, wherein such questions of open-endedness are explored for advancing AI, whatever the nature of the underlying search algorithm (e.g. evolutionary or gradient-based). For example, open-ended search might design new architectures for neural networks, new reinforcement learning algorithms, or most ambitiously, aim at designing artificial general intelligence. This paper proposes that open-ended evolution and artificial life have much to contribute towards the understanding of open-ended AI, focusing here in particular on the safety of open-ended search. The idea is that AI systems are increasingly applied in the real world, often producing unintended harms in the process, which motivates the growing field of AI safety. This paper argues that open-ended AI has its own safety challenges, in particular, whether the creativity of open-ended systems can be productively and predictably controlled. This paper explains how unique safety problems manifest in open-ended search, and suggests concrete contributions and research questions to explore them. The hope is to inspire progress towards creative, useful, and safe open-ended search algorithms.