Thoughts on Human Models
This is a joint post by MIRI Research Associate and DeepMind Research Scientist Ramana Kumar and MIRI Research Fellow Scott Garrabrant, cross-posted from the AI Alignment Forum and LessWrong.
Human values and preferences are hard to specify, especially in complex domains. Accordingly, much AGI safety research has focused on approaches to AGI design that refer to human values and preferences indirectly, by learning a model that is grounded in expressions of human values (via stated preferences, observed behaviour, approval, etc.) and/or real-world processes that generate expressions of those values. There are additionally approaches aimed at modelling or imitating other aspects of human cognition or behaviour without an explicit aim of capturing human preferences (but usually in service of ultimately satisfying them). Let us refer to all these models as human models.
In this post, we discuss several reasons to be cautious about AGI designs that use human models. We suggest that the AGI safety research community put more effort into developing approaches that work well in the absence of human models, alongside the approaches that rely on human models. This would be a significant addition to the current safety research landscape, especially if we focus on working out and trying concrete approaches as opposed to developing theory. We also acknowledge various reasons why avoiding human models seems difficult.
Problems with Human Models
To be clear about human models, we draw a rough distinction between our actual preferences (which may not be fully accessible to us) and procedures for evaluating our preferences. The first thing, actual preferences, is what humans actually want upon reflection. Satisfying our actual preferences is a win. The second thing, procedures for evaluating preferences, refers to various proxies for our actual preferences such as our approval, or what looks good to us (with necessarily limited information or time for thinking). Human models are in the second category; consider, as an example, a highly accurate ML model of human yes/no approval on the set of descriptions of outcomes. Our first concern, described below, is about overfitting to human approval and thereby breaking its connection to our actual preferences. (This is a case of Goodhart’s law.)