For a wide range of applications of knowledge seeking, the best available wisdom centrally involves what can be called an inquiry complex: a structured set of questions around a central question that experts tend to agree you are on the hook for if you are going to have a serious view on the central question. Such an inquiry complex does not depend on there being a recognized settled answer; inquiry complexes around central question of philosophy or the cutting edge of science almost by definition do not have a recognized settled answer. This project explores if such inquiry complexes can be usefully captured by an LLM. The first proof-of-concept will aim to model philosophical inquiry around the concept of knowledge itself. By structuring AI to engage with inquiry complexes, we envision a system that goes beyond regurgitating facts. Potential applications range from the transmission of culture and values-based practice in medicine, to supporting scientific theory building and new models of organizing social media for collective reasoning.
Header Image Source: Wellcome Collection gallery (2018-04-05)