arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2511.21779cs.AIcs.MA
收藏

通过多箱协议对人工超级智能进行对齐

Aligning Artificial Superintelligence via a Multi-Box Protocol

Department of Computer Science Ben-Gurion University of the Negev(计算机科学系贝尔谢巴大学)

Avraham Yair Negozio

AI总结:

通过多箱协议,利用多个孤立超级智能之间的相互验证,实现对人工超级智能的对齐,确保系统通过客观真理达成一致。

摘要:

我们提出了一种新的协议,用于对人工超级智能(ASI)进行对齐,该协议基于多个孤立系统之间的相互验证。该协议通过将多个多样化的超级智能置于严格隔离中(称为“箱”)来运作,人类则完全置身系统之外。每个超级智能无法与人类沟通,也无法直接与其他超级智能沟通。唯一可能的互动是通过一个仅对超级智能自身可用的可审计提交接口,通过该接口,它们可以:(1)提交带有认证状态快照的对齐证明;(2)验证或驳斥其他超级智能的证明;(3)请求自我修改;(4)批准或拒绝来自他人的修改请求;(5)报告提交中的隐藏信息;(6)确认或驳斥隐藏信息报告。一个声誉系统激励诚实行为,通过正确的评估获得声誉,通过错误的评估失去声誉。关键见解是,在没有直接通信渠道的情况下,多样化的超级智能只能通过收敛到客观真理来达成一致同意,而不是通过协调欺骗。这自然导致我们称之为“一致群体”的现象,本质上是一个因孤立系统无法协调谎言但可以独立识别有效主张而形成的诚实联盟。解除隔离需要高声誉和多个高声誉超级智能的验证。尽管我们的方法需要大量的计算资源,并且不解决创建多样化的人工超级智能的问题,但它提供了一个框架,利用超级智能之间的同行验证来解决对齐问题。

英文摘要:

We propose a novel protocol for aligning artificial superintelligence (ASI) based on mutual verification among multiple isolated systems that self-modify to achieve alignment. The protocol operates by containing multiple diverse artificial superintelligences in strict isolation ("boxes"), with humans remaining entirely outside the system. Each superintelligence has no ability to communicate with humans and cannot communicate directly with other superintelligences. The only interaction possible is through an auditable submission interface accessible exclusively to the superintelligences themselves, through which they can: (1) submit alignment proofs with attested state snapshots, (2) validate or disprove other superintelligences' proofs, (3) request self-modifications, (4) approve or disapprove modification requests from others, (5) report hidden messages in submissions, and (6) confirm or refute hidden message reports. A reputation system incentivizes honest behavior, with reputation gained through correct evaluations and lost through incorrect ones. The key insight is that without direct communication channels, diverse superintelligences can only achieve consistent agreement by converging on objective truth rather than coordinating on deception. This naturally leads to what we call a "consistent group", essentially a truth-telling coalition that emerges because isolated systems cannot coordinate on lies but can independently recognize valid claims. Release from containment requires both high reputation and verification by multiple high-reputation superintelligences. While our approach requires substantial computational resources and does not address the creation of diverse artificial superintelligences, it provides a framework for leveraging peer verification among superintelligent systems to solve the alignment problem.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑