Affiliation:
1. Cardiff University, UK
Abstract
Large Language Models (LLMs) and generative Artificial Intelligence (A.I.) have become the latest disruptive digital technologies to breach the dividing lines between scientific endeavour and public consciousness. LLMs such as ChatGPT are platformed through commercial providers such as OpenAI, which provide a conduit through which interaction is realised, via a series of exchanges in the form of written natural language text called ‘prompt engineering’. In this paper, we use Membership Categorisation Analysis to interrogate a collection of prompt engineering examples gathered from the endogenous ranking of prompting guides hosted on emerging generative AI community and practitioner-relevant social media. We show how both formal and vernacular ideas surrounding ‘natural’ sociological concepts are mobilised in order to configure LLMs for useful generative output. In addition, we identify some of the interactional limitations and affordances of using role prompt engineering for generating interactional stances with generative AI chatbots and (potentially) other formats. We conclude by reflecting the consequences of these everyday social-technical routines and the rise of ‘ethno-programming’ for generative AI that is realised through natural language and everyday sociological competencies.