English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Artificial life originated and has long studied the topic of open-endedevolution, which seeks the principles underlying artificial systems thatinnovate continually, inspired by biological evolution. Recently, interest hasgrown within the broader field of AI in a generalization of open-endedevolution, here called open-ended search, wherein such questions ofopen-endedness are explored for advancing AI, whatever the nature of theunderlying search algorithm (e.g. evolutionary or gradient-based). For example,open-ended search might design new architectures for neural networks, newreinforcement learning algorithms, or most ambitiously, aim at designingartificial general intelligence. This paper proposes that open-ended evolutionand artificial life have much to contribute towards the understanding ofopen-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, oftenproducing unintended harms in the process, which motivates the growing field ofAI safety. This paper argues that open-ended AI has its own safety challenges,in particular, whether the creativity of open-ended systems can be productivelyand predictably controlled. This paper explains how unique safety problemsmanifest in open-ended search, and suggests concrete contributions and researchquestions to explore them. The hope is to inspire progress towards creative,useful, and safe open-ended search algorithms.

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