開放性對於人工超人類智能至關重要。

Open-Endedness is Essential for Artificial Superhuman Intelligence

June 6, 2024

作者: Edward Hughes, Michael Dennis, Jack Parker-Holder, Feryal Behbahani, Aditi Mavalankar, Yuge Shi, Tom Schaul, Tim Rocktaschel

cs.AI

摘要

近年來，人工智慧系統的整體能力有了巨大的提升，主要是通過在互聯網規模數據上訓練基礎模型所推動的。然而，創建一個開放式、不斷自我改進的人工智慧仍然是一個難以捉摸的目標。在這篇立場論文中，我們認為現在已經具備了實現人工智慧系統對於人類觀察者具有開放性的條件。此外，我們主張這種開放性是任何人工超人類智慧（ASI）的基本特性。我們首先通過新奇性和可學習性的角度提供了開放性的具體形式定義。然後，我們通過在基礎模型之上構建的開放式系統展示了通往ASI的途徑，這些系統能夠進行新穎的、與人類相關的發現。最後，我們通過檢視一般能力的開放式人工智慧的安全影響來結論。我們預計，開放式基礎模型將在不久的將來被證明是一個日益豐富且安全關鍵的研究領域。

English

In recent years there has been a tremendous surge in the general capabilities of AI systems, mainly fuelled by training foundation models on internetscale data. Nevertheless, the creation of openended, ever self-improving AI remains elusive. In this position paper, we argue that the ingredients are now in place to achieve openendedness 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, humanrelevant discoveries. We conclude by examining the safety implications of generally-capable openended 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.