Raiding the inarticulate since 2010

accelerated academy acceleration agency AI Algorithmic Authoritarianism and Digital Repression archer Archive Archiving artificial intelligence automation Becoming Who We Are Between Post-Capitalism and Techno-Fascism big data blogging capitalism ChatGPT claude Cognitive Triage: Practice, Culture and Strategies Communicative Escalation and Cultural Abundance: How Do We Cope? Corporate Culture, Elites and Their Self-Understandings craft creativity critical realism data science Defensive Elites Digital Capitalism and Digital Social Science Digital Distraction, Personal Agency and The Reflexive Imperative Digital Elections, Party Politics and Diplomacy digital elites Digital Inequalities Digital Social Science Digital Sociology digital sociology Digital Universities elites Fragile Movements and Their Politics Cultures generative AI higher education Interested labour Lacan Listening LLMs margaret archer Organising personal morphogenesis Philosophy of Technology platform capitalism platforms Post-Democracy, Depoliticisation and Technocracy post-truth psychoanalysis public engagement public sociology publishing Reading realism reflexivity scholarship sexuality Shadow Mobilization, Astroturfing and Manipulation Social Media Social Media for Academics social media for academics social ontology social theory sociology technology The Content Ecosystem The Intensification of Work theory The Political Economy of Digital Capitalism The Technological History of Digital Capitalism Thinking trump twitter Uncategorized work writing zizek

Ask an LLM: who wrote this unpublished text?

An experiment to test how visible an author is within a language model: give the model a page of unpublished writing and ask it to identify the author. I just presented Claude Opus 4.5 with a draft page and asked it to identify the source. This is what it came back with:

This reads like academic writing, likely from a sociologist or social theorist working on technology and everyday life. Several clues point to the author’s identity and background:

  1. The citation of Margaret Archer (2000) and the specific use of her terminology (“the practical order,” “subject/object relations”) suggests someone working within critical realist sociology or adjacent theoretical traditions.
  2. The writing style combines first-person vignette with theoretical analysis—a common approach in qualitative sociology and science and technology studies (STS).
  3. The substantive focus on how AI reshapes mundane, “quotidian” practices and our relationship to knowledge suggests someone interested in the sociology of knowledge, technology, or digital culture.
  4. The phrase “frontier models” and the nuanced concern about the sustainability of open web resources for training data indicates someone who follows AI developments closely and is writing relatively recently (2023-2024).

Given the Archer citation, the British English spelling (“repressurise,” “recognise”), and the theoretical sophistication combined with attention to everyday practice, my best guess would be Mark Carrigan—a British sociologist who works extensively on digital technology, social media, and has written about AI’s social implications. He’s known for exactly this style of combining personal observation with Archerian social theory.

If not Carrigan specifically, it’s almost certainly someone in UK-based sociology with ties to critical realism and an interest in digital life. Does that match who you had in mind?

I’m assuming it’s not cheating by inferring this from my account details. I’m reasonably confident this isn’t technically possible when I have personalisation settings turned off. I’m also unsure how it would necessarily infer I’m the author from the prompt “who do you think wrote this text?” given that personalisation is about declarative memory and cross-thread searching rather than training on user prompts.

, , , ,
,