English(EN) Fundamental Impossibility Results in AI Safety: Trading Off between Desiderata

AI安全研究揭示了有用性和无害性之间的根本性权衡

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-21 04:00

一篇新发表在arXiv上的论文探讨了AI安全中不同期望特性之间固有的权衡，例如确保AI系统既无害又有用。该研究将AI交互形式化为一个涉及防御者、攻击者和AI本身的“三方博弈”，证明了在提供有用建议的同时维护公共安全之间存在根本性冲突。作者还研究了操纵共享信息以专门使防御者受益的方法，并讨论了设计更安全AI系统的相关影响。 AI

影响强调了AI安全设计中的理论局限性，暗示了同时优化多种期望AI行为所面临的挑战。

排序理由该集群包含一篇详细介绍AI安全理论结果的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍AI安全理论结果的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 2 days old; Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Ida Mattsson, Ratip Emin Berker, Emanuel Tewolde, Ioannis Anagnostides, Kiriaki Fragkia, Xinyu Liu, Alexander Heckett, Jiayuan Liu, Eden Hartman, Vojt\v{e}ch Kova\v{r}\'{i}k, Sven Neth, Maria-Florina Balcan, Tuomas Sandholm, Vincent Conitzer · 2026-10-21 04:00

AI安全中的根本性不可能定理：在期望之间进行权衡

arXiv:2610.27373v1 Announce Type: cross Abstract: Is there a fundamental tradeoff between desiderata for safe AI systems, such as harmlessness and helpfulness? We answer by formalizing the interaction between AI systems and users as a game with three players: a defender and an at…

本文如何被排名

报道来源 [1]

AI安全中的根本性不可能定理：在期望之间进行权衡

相关实体

相关话题