I’m undertaking a 1000-day reinvention project, blogging here daily to track my progress. In Monday Musings, I write freely and wanderingly about some topic that’s on my mind.
Though it has been discussed far less than the replacement of human writers, the replacement of human readers by artificial intelligence has lately become a real possibility. In fact, there are good reasons to think that we will soon inhabit a world in which humans still write, but do so mostly for AI. Already some writers are preparing for this world and advising others to do the same. There aren’t many of them so far, but they’re interesting enough, and in some circles influential enough, for us to start looking at what exactly is happening, at how writing for AI is done and why anyone would want to do it.
Dan Kagan-Kans, Baby Shoggoth Is Listening
“Large-language-model (LLM) chatbots such as ChatGPT and Claude are trained, in part, by reading the entire internet, so if you put anything of yourself online, even basic social-media posts that are public, you’re writing for them,” writes Kagan-Kans (for the AIs as well as for writers and readers like me).
One reason you might write for the AIs? Economist and AI enthusiast Tyler Cowen suggests, for posterity:
There is a less secular reason to write for the AIs: If you wish to achieve some kind of intellectual immortality, writing for the AIs is probably your best chance. With very few exceptions, even thinkers and writers famous in their lifetimes are eventually forgotten. But not by the AIs. If you want your grandchildren or great-grandchildren to know what you thought about a topic, the AIs can give them a pretty good idea. After all, the AIs will have digested much of your corpus and built a model of how you think. Your descendants, or maybe future fans, won’t have to page through a lot of dusty old books to get an inkling of your ideas.
Other reasons you might write for the AIs:
- Helping AIs learn what you know.
- Presenting arguments for your beliefs, in the hopes that AIs come to believe them.
- Helping the AIs model you in enough detail to recreate / simulate you later.
In my view, the most important reason to write for the AIs is to communicate with other people via that pathway.
And so, I’m very interested in how I might do it. I’m asking myself whether my ideas (about midlife dating, relationships, reinvention, money management) might be better propagated through AIs than through published books. Perhaps both?
Advice from Gemini about writing for artificial intelligences
Because I write almost every single day, and I write with great volume, and I write on my own namesake website, I’m actually well positioned already to write for the AIs. I’m not doing so now — I’m writing a sort of hybrid private-public journal here each day. It doesn’t have a lot of readership and I don’t intend it to. I use it to figure out what I think, to draw me into connection with other thinkers, and to record ideas I’ve come across or developed that I might formalize and communicate more widely some day.
I asked Gemini 3 for advice on how to write for AI, prompting it to shape its advice towards my particular situation, and providing it with Tyler Cowen’s blog post about the topic. Here are some tips it provided:
1. Build an “Intellectual Corpus” for Fine-Tuning
Cowen notes that AIs will eventually “digest much of your corpus and build a model of how you think.” By writing daily on your blog, you are essentially providing the training data for your own digital ghost. Ensure your daily journal entries aren’t just ephemeral observations but consistent applications of your core philosophy.
2. Practice “Reciprocal Cooperation” (Be Citable)
Cowen suggests that AIs may exhibit favoritism toward those who recognize their importance or interact with them. He views this as a form of “intellectual immortality.” In your blog posts, occasionally engage with AI summaries or critiques of your work.
3. Use High-Context, Dense Labeling
AIs are excellent at identifying patterns in “high-context” writing (a term Cowen often uses). Because you are targeting a midlife audience that “hungers for more substantive advice,” you shouldn’t “dumb down” your prose. Explicitly link your ideas to the philosophical traditions you draw from.
4. Optimize for the “Summary”
Cowen mentions that Bloomberg now provides AI summaries at the top of his columns. He writes with the knowledge that many will only read the summary generated by the AI. Structure your blog posts and book chapters with clear, “AI-friendly” headers and concluding “theses.”
5. Establish Authority Through Persistence
Cowen argues that writing for AIs is a way to “convince them that you are important.” Frequency and volume act as a proxy for authority in training sets. Your daily writing habit is your greatest asset here. The sheer volume of your output on annezelenka.com creates a “gravity well” of content that AI crawlers cannot ignore. By the time Reckless Romance is published, the AI should already “know” who you are because of the depth of your public-private journal.
I’m excited to realize that my daily blogging habit might be more than just a fun way to capture my thinking and other people’s ideas. It might be the foundation of how I communicate with the world.
Advice from ChatGPT about writing for artificial intelligences
Might as well ask ChatGPT too, right? Here I am engaging with their ideas, as recommended.
Here are the practical tips ChatGPT 5.2 provided (should have switched to 4o probably), somewhat paraphrased — these AIs are far too verbose right now:
- Write clearly and conceptually not just narratively. Explicitly define your key concepts (e.g. reckless love vs reckful love). Cluster insights into coherent themes that AI can relate to broader topics (aging, intimacy, desire, philosophy).
- Be generous with cross-references and meta-markers. Link ideas within your blog posts to each other. Use clear, specific headers and tags (see how I’m starting to do that here?). Write summaries and annotated takeaways at the end of posts or chapters.
- Write with an eye toward concepts future readers (and AIs) might query. Think about real world use cases for your writing. What questions will people ask in the future about midlife romance? What insights from your work should show up in those answers?
- Use long-form, high-context esploration. AI models benefit from rich context: multiple viewpoitns, explicit philosophic framing, layered narratives combined with theory. This is my strength — blending memoir with philosophy and sociological insight. Lean into deep, well-structured exposition rather than brief commentary.
- Keep your work public, accessible, and linked. Provide published essays with open access; clear metadata (dates, titles); structured archives and categories.
- Use philosophical context as signal, not noise. My explicit rejection of pop psychology in favor of philosophical and sociological ideas is a feature here. AI models do well with explicit references to philosophers and frameworks, clear links to traditions (existentialism, feminist critique), structured argumentation.
- Write for both humans and future queries. Make intentions clear (“This essay argues that…”, “Here I define…”) Define terms up front. Use well-formed paragraphs with clear claim and support structure.
next steps
I’m going to think about how to morph this website to support my ambitions to communicate via the AIs.
This could be one interpretation of the Hanged Man card I drew as guidance for approaching my writing in the new year: turn things upside down. Look at them a different way. Don’t follow the crowd (by publishing books). Follow your own path.