Suppose there are no in-principle restrictions on the contents of arbitrarily intelligent agents’ goals. According to “instrumental convergence” arguments, potentially scary things follow. I do two things in this paper. First, focusing on the influential version of the instrumental convergence argument due to Nick Bostrom, I explain why such arguments require an account of “promotion”, i.e., an account of what it is to “promote” a goal. Then, I consider whether extant accounts of promotion in the literature—in particular, probabilistic and fit-based views of promotion—can be used to support dangerous instrumental convergence. I argue that neither account of promotion can do the work. The opposite is true: accepting either account of promotion undermines support for instrumental convergence arguments’ existentially worrying conclusions. The conclusion is that we needn’t be scared—at least not because of arguments concerning instrumental convergence.

假设对任意智能代理的目标内容没有原则上的限制。根据“工具趋同”的论点，可能可怕的事情接踵而至。我在这篇论文中做了两件事。首先，专注于 Nick Bostrom 提出的工具收敛论证的有影响力的版本，我解释了为什么这样的论点需要解释“促进”，即解释“促进”目标是什么。然后，我考虑文献中现存的关于晋升的描述——特别是基于概率和契合度的晋升观点——是否可以用来支持危险的工具性趋同。我认为，任何一个关于晋升的说法都不能起到作用。事实恰恰相反：接受任何一种促进的说法都会削弱对工具性趋同论证的存在性担忧结论的支持。结论是，我们不需要害怕——至少不需要因为关于工具趋同的争论。