This paper examines the challenges associated with achieving life-long
superalignment in AI systems, particularly large language models (LLMs).
Superalignment is a theoretical framework that aspires to ensure that
superintelligent AI systems act in accordance with human values and goals.
Despite its promising vision, we argue that achieving superalignment requires
substantial changes in the current LLM architectures due to their inherent
limitations in comprehending and adapting to the dynamic nature of these human
ethics and evolving global scenarios. We dissect the challenges of encoding an
ever-changing spectrum of human values into LLMs, highlighting the
discrepancies between static AI models and the dynamic nature of human
societies. To illustrate these challenges, we analyze two distinct examples:
one demonstrates a qualitative shift in human values, while the other presents
a quantifiable change. Through these examples, we illustrate how LLMs,
constrained by their training data, fail to align with contemporary human
values and scenarios. The paper concludes by exploring potential strategies to
address and possibly mitigate these alignment discrepancies, suggesting a path
forward in the pursuit of more adaptable and responsive AI systems.

探讨实现 AI 系统中的终身超对齐所面临的挑战，特别是大型语言模型（LLMs）；超对齐是一个理论框架，旨在确保超级智能 AI 系统按照人类的价值观和目标行动；我们认为实现超对齐需要对当前 LLM 体系结构进行重大改变，因为它们在理解和适应人类伦理和不断变化的全球情景的能力上存在固有的局限性；通过分析两个不同的例子，我们阐明 LLM 面对训练数据的限制，无法与当代人类价值观和情景相契合；最后，本文探讨了解决和可能减轻这种对齐差异的潜在策略，提出了追求更适应和响应性的 AI 系统的路径。