按年被提到
20262026 · 7 次2026
AI 安全、伦理与社会影响›AI 风险与对齐·arXiv:2602.14740 · cs.AI

AI Arms and Influence: Frontier Models Exhibit Sophisticated Reasoning in Simulated Nuclear Crises

Kenneth Payne · 2026
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 7 人首次 2026-02-17 · 最近 2026-06-11
7不同的人
2活跃月份
4讨论串
11被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Today's leading AI models engage in sophisticated behaviour when placed in strategic competition. They spontaneously attempt deception, signaling intentions they do not intend to follow; they demonstrate rich theory of mind, reasoning about adversary beliefs and anticipating their actions; and they exhibit credible metacognitive self-awareness, assessing their own strategic abilities before deciding how to act. Here we present findings from a crisis simulation in which three frontier large language models (GPT-5.2, Claude Sonnet 4, Gemini 3 Flash) play opposing leaders in a nuclear crisis. Our simulation has direct application for national security professionals, but also, via its insights into AI reasoning under uncertainty, has applications far beyond international crisis decision-making. Our findings both validate and challenge central tenets of strategic theory. We find support for Schelling's ideas about commitment, Kahn's escalation framework, and Jervis's work on misperception, inter alia. Yet we also find that the nuclear taboo is no impediment to nuclear escalation by our models; that strategic nuclear attack, while rare, does occur; that threats more often provoke counter-escalation than compliance; that high mutual credibility accelerated rather than deterred conflict; and that no model ever chose accommodation or withdrawal even when under acute pressure, only reduced levels of violence. We argue that AI simulation represents a powerful tool for strategic analysis, but only if properly calibrated against known patterns of human reasoning. Understanding how frontier models do and do not imitate human strategic logic is essential preparation for a world in which AI increasingly shapes strategic outcomes.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论sestep · 2026-06

“This is just false. The article links to the 46-page paper [1] which lists full prompts in section E.2. [1] https://arxiv.org/pdf/2602.14740”

Shall we play a game? – LLMs use tactical nukes in 95% of simulations原评论 ↗
评论gus_massa · 2026-06

“I agree, it's also not published in a journal, only in the arxiv. Some articles in the arxiv are good and other are just a blog post formatted in two columns inside a pdf. Anyway, it links to https://arxiv.org/abs/2602.14740 that links to https://github.com/kennethpayne01/project_kahn_public in particular someone already complained https://github.co…”

Shall we play a game? – LLMs use tactical nukes in 95% of simulations原评论 ↗
评论urbnspacecowboy · 2026-06

“Paper: "AI Arms and Influence: Frontier Models Exhibit Sophisticated Reasoning in Simulated Nuclear Crises" https://arxiv.org/abs/2602.14740 Code and full results: https://github.com/kennethpayne01/project_kahn_public”

Shall we play a game? – LLMs use tactical nukes in 95% of simulations原评论 ↗
评论Majromax · 2026-06

“This blog post is based on a paper (https://arxiv.org/abs/2602.14740). The paper is based on a simulated wargame. The wargame is of the author's own design. The wargame design does not differentiate between ordinary defeat and mutually assured destruction, so of course a player about to use would 'push the button.' That's also believed to be true in real…”

Shall we play a game? – LLMs use tactical nukes in 95% of simulations原评论 ↗
被提交为 story · 3 次