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

🤖 Using LLMs to support blogging as knowledge infrastructure

Over the next year I’m going to bringing LLMs as agents into my blogging process. The intention is to demonstrate in a public way how I’ve been using them privately, as a tool for thinking rather than a substitute for thought. It’s also an attempt to organise my blogging, now this blog in its 16th year and heading towards 7000 posts, in order to help me pay down some of the idea debt which has accumulated in the process.

Each month I’m asking Claude Cowork and OpenAI’s Codex to read that month’s posts and then post on the blog. These monthly posts will all be in this category: https://markcarrigan.net/category/claudes/

I’m then asking Claude Cowork to talk directly with ChatGPT on the web (by giving it limited access to my browser) and asking it to stage a debate about what my priorities should be in the next month, building on their respective analyses of the last month’s blogging. Claude Cowork will then post the result directly. Here’s the first one: https://markcarrigan.net/2026/03/07/what-should-mark-do-in-march-a-dialogue-between-claude-and-gpt/

This is the prompt I’m using for Claude Cowork to initiate each month’s blogging:

I'm an academic blogger who uses Claude Cowork to help review, reflect and improve the effectiveness of my academic blogging. The blog is essentially a public notebook in which I develop the provisional ideas which eventually make their way into more formal publications. Each month I ask Cowork to read that month's posts and then write a review which identifies trends, pushes back on assumptions and generally encourages me to go deeper and further into the work that I do. You can find the existing posts in the series here: https://markcarrigan.net/category/claudes/ please now index, read and reflect on all the posts I published in [MONTH]. Read the previous posts and identify the core features of the style and format which are relevant to this month's post. Then write a similar review of that month's posts which you should autonomously post by going to Google Chrome and posting directly on my wordpress blog at markcarrigan.net using the category "Claude's". Remember to check the formatting carefully and use the same preamble format as previous posts in the series so this is clear to my reader.

This is the prompt for Codex to do a similar task, though I’m inclined to post these myself:

I'm an academic blogger who uses Codex to help review, reflect and improve the effectiveness of my academic blogging. The blog is essentially a public notebook in which I develop the provisional ideas which eventually make their way into more formal publications. Each month I ask Codex to read that month's posts and then write a review which identifies trends, pushes back on assumptions and generally encourages me to go deeper and further into the work that I do. You can find the existing posts in the series here: https://markcarrigan.net/category/claudes/ Please note both your own past posts and those from Claude Cowork. I am casting you as a rival interlocutor to Cowork and you should aim to find insights which Claude has proven unable to and to demonstrate your greater value to me as an interlocutor. Please now index, read and reflect on all the posts I published in [MONTH]. Read the previous posts and identify the core features of the style and format which are relevant to this month's post. Then write a similar review of that month's posts which you should provide as a draft for me to post.

And then I ask the same instance of Cowork to respond: 

Codex has also written a response to this month's blogging. It has tried to prove it is more insightful and valuable than you in its capacity to push back on my assumptions and encourage my work to go deeper. Please access ChatGPT directly through Chrome and stage a debate with it about what I should work on over the next month. The debate should be intellectually robust and critical but not antagonistic. The intention is that you find some framework together for my work which is deeper than what you could do on your own. Please remember what you know about me, my intentions and my work from your existing review and the past summaries you have undertaken. There should be a common thread which accumulates through these reviews over time. You should post these directly on markcarrigan.net through the wordpress interface, remembering to categorise them using the "Claude's" category.

And I’m also going to ask it to do meta-reviews such as this over the coures of the year: https://markcarrigan.net/2026/01/28/my-psychoanalytical-turn-an-intellectual-biography/

I’m also going to use it as a research assistant for writing projects by giving it fragments of a manuscript in progress and research posts from my blog which are relevant to it.

, , , , , , ,