View Proposal

---

Proposer

Alessandro Suglia

Title

Open-Endedness is Essential for Artificial Superhuman Intelligence

Goal

Explore open-ended AI literature and work on open-ended learning systems

Description

In recent years there has been a tremendous surge in the general capabilities of AI systems, mainly fuelled by training foundation models on internet-scale data. Nevertheless, the creation of open-ended, ever self-improving AI remains elusive. In this position paper, we argue that the ingredients are now in place to achieve open-endedness in AI systems with respect to a human observer. Furthermore, we claim that such open-endedness is an essential property of any artificial superhuman intelligence (ASI). We begin by providing a concrete formal definition of open-endedness through the lens of novelty and learnability. We then illustrate a path towards ASI via open-ended systems built on top of foundation models, capable of making novel, human-relevant discoveries. We conclude by examining the safety implications of generally-capable open-ended AI. We expect that open-ended foundation models will prove to be an increasingly fertile and safety-critical area of research in the near future.

Resources

https://arxiv.org/abs/2406.04268

Background

Url

Difficulty Level

Challenging

Ethical Approval

None

Number Of Students

1

Supervisor

Alessandro Suglia

Keywords

deep learning, neural networks, language models, ai

Degrees

Master of Science in Artificial Intelligence
Master of Science in Data Science
Master of Science in Human Robot Interaction
Master of Science in Robotics
Master of Science in Robotics with Industrial Application