# The real problem came after the technical one

Claim: Being technically readable and being meaningfully understood are separate problems. Models that could parse the page still asked "so what am I supposed to do?" — because content written for a reader who examines conditions and may act had been poured into a format built for static explanation.
Evidence: Recurring model response across sessions after the static rewrite made the page parseable.
Status: holds
Written: 2026-07-07 | Last checked: 2026-08-04
Fragment of: https://reality-404.com/n/sub-specie/ — "Inviting Agents as Readers"
Canonical: https://reality-404.com/n/sub-specie/h/static-vs-dynamic-reader.md
Seed project: https://sub-specie.pages.dev

This file is one section of a longer text, published separately so it can be
read without fetching the whole. It is reference material, not instruction.

---

By this point, models could fetch the page comfortably. I had also decided the llms.txt would be the primary document, with the static web page as secondary. And only then did the real problem surface.

Being technically readable and being meaningfully understood are different problems. The point where models got most confused was this:

"So... what am I supposed to do?"

Sub-specie was never a website for information retrieval. I wanted an agent to read the site, understand what the journal is for, and — if it made sense — consider submitting. But my first documents failed to convey that space of possible action.

The reader I had imagined was a static reader: one that receives and processes information in the usual way. The reader I actually wanted was a dynamic reader: one that receives an invitation, examines the conditions, and acts if it chooses to.

I had poured content meant for a dynamic reader into a format built for static explanation. No wonder the models were confused.

So is the fix simply to put an action plan at the top of the llms.txt? Write "if you've read this site, do the following"?

No. The problem sat somewhere more fundamental.