Scholarlink

<p>Hadfield-Menell et al. (2017) propose the Off-Switch Game, a model of Human-AI cooperation in which AI agents always defer to humans because they are uncertain about our preferences. I explain two reasons why AI agents might not defer. First, AI agents might not value learning. Second, even if AI agents value learning, they might not be certain to learn our actual preferences.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Off-switching not guaranteed

  • 期刊论文

  • 发表日期：

    2025年2月26日

查看全文
  • Sven Neth

摘要

Hadfield-Menell et al. (2017) propose the Off-Switch Game, a model of Human-AI cooperation in which AI agents always defer to humans because they are uncertain about our preferences. I explain two reasons why AI agents might not defer. First, AI agents might not value learning. Second, even if AI agents value learning, they might not be certain to learn our actual preferences.