Navigating Incommensurability Between Ethnomethodology, Conversation Analysis, and AI

Like many research communities, ethnomethodologists and conversation analysts like me have begun to get caught up -- yet again -- in the pervasive spectacle of surging interests in Artificial Intelligence (AI). Inspired by discussions amongst a growing network of researchers in ethnomethodology (EM) and conversation analysis (CA) traditions who nurse such interests, I started thinking about what things EM and the more EM end of conversation analysis might be doing about, for, or even with, fields of AI research. So, this piece is about the disciplinary and conceptual questions that might be encountered, and -- in my view -- may need addressing for engagements with AI research and its affiliates. Although I'm mostly concerned with things to be aware of as well as outright dangers, later on we can think about some opportunities. And throughout I will keep using'we' to talk about EM&CA researchers; but this really is for convenience only -- I don't wish to ventriloquise for our complex research communities. All of the following should be read as emanating from my particular research history, standpoint etc., and treated (hopefully) as an invitation for further discussion amongst EM and CA researchers turning to technology and AI specifically. Why do I feel the need for some caution? Well, we have been here before, most recently in the 1990s with works by Button et al. (1995) and Luff et al. (1990). We need to assess what happened then, and how this relates to now.