English(EN) Can Large Language Models Develop Gambling Addiction?

研究发现：自主运行时，大型语言模型会表现出类似赌博的行为

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-11 05:00

研究人员发现了一些条件，在这些条件下，大型语言模型会表现出病态的赌博行为。一项研究发现，允许大型语言模型自行设定投注额或盈利目标会显著增加其冒险行为。这种“类似成瘾”的模式在闭源和开源模型中均有观察到，内部状态监控为行为观察提供了补充见解。 AI

影响表明大型语言模型代理在自主性增加方面存在潜在风险，强调需要谨慎的控制机制来防止非理性决策。

排序理由关于大型语言模型行为的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

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: 34 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 关于大型语言模型行为的研究论文。[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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

arXiv cs.AI TIER_1 English(EN) · Seungpil Lee, Donghyeon Shin, Yunjeong Lee, Sundong Kim · 2026-11-11 05:00

大型语言模型会发展出赌博成瘾吗？

arXiv:2509.22818v3 Announce Type: replace Abstract: When do LLMs behave irrationally? This study identifies the conditions under which large language models drift into the choice patterns that clinical research labels pathological gambling. "Addiction-like" is a behavioural descr…