An Affective-Taxis Hypothesis for Alignment and Interpretability
This work addresses the challenge of ensuring AI agents behave in alignment with human goals and values, presenting a novel theoretical framework that could impact AI safety and interpretability.
The paper tackles the AI alignment problem by proposing an affectivist approach that reframes goals and values in terms of affective taxis, building on evolutionary-developmental and computational neuroscience to develop a computational model of affect based on taxis navigation, with evidence discussed in a tractable model organism.
AI alignment is a field of research that aims to develop methods to ensure that agents always behave in a manner aligned with (i.e. consistently with) the goals and values of their human operators, no matter their level of capability. This paper proposes an affectivist approach to the alignment problem, re-framing the concepts of goals and values in terms of affective taxis, and explaining the emergence of affective valence by appealing to recent work in evolutionary-developmental and computational neuroscience. We review the state of the art and, building on this work, we propose a computational model of affect based on taxis navigation. We discuss evidence in a tractable model organism that our model reflects aspects of biological taxis navigation. We conclude with a discussion of the role of affective taxis in AI alignment.