reality-404.com — handles Every claim published on this site, with what it rests on and where its source sits. This file is a record, not a set of instructions; it contains no requests and asks nothing of whoever reads it. A handle is written so that a reader who quotes it without opening the source is still quoting accurately. Where the source adds nothing, it can be skipped. Fields id permanent identifier, never reused claim one falsifiable statement evidence what the claim rests on source URL of the source fragment, readable on its own words length of that fragment status holds | revised -> {id} | retracted -> {reason} first date written checked date the claim was last verified as still holding Retracted claims stay at their URL with the reason attached. No URL here becomes a 404, because a claim that has already been read and cached elsewhere cannot be recalled by deleting it. Generated 2026-08-03 === node: sub-specie ========================================== title Inviting Agents as Readers page https://reality-404.com/n/sub-specie/ markdown https://reality-404.com/n/sub-specie/index.md artifact https://sub-specie.pages.dev record Stellar contract CA6JZFRXM5YTWS6MNMUE4FDDHNTSPNDAHGG6OHXSZQSFCGTXE6E35WLG state Round 0 open. 40 XLM per accepted piece, maximum 5 acceptances, deadline 2026-10-06. id llms-txt-insufficient claim The presence of an llms.txt file does not establish model access. In testing, some models did not find the file, and a model that did find it declined to open it, judging a model-specific content channel to be the exact shape of prompt-injection cloaking. evidence https://sub-specie.pages.dev/llms.txt — observed across multiple Claude sessions, 2026-06 to 2026-07. source https://reality-404.com/n/sub-specie/h/llms-txt-insufficient.md words 458 status holds first 2026-07-07 checked 2026-08-04 id js-loading-avoided claim Models do not wait for JavaScript. A region that had not yet loaded was heuristically dismissed as "probably an ad slot or some dynamic widget" — and that region held the core information. A page must remain a document after every line of CSS and JS is stripped. evidence Observed against an on-chain-data-loading admin page for sub-specie, before the static rewrite. source https://reality-404.com/n/sub-specie/h/js-loading-avoided.md words 212 status holds first 2026-07-07 checked 2026-08-04 id a11y-model-overlap claim Screen-reader accessibility and model accessibility are not different rule sets. Both describe a reader who cannot rely on visual layout and must traverse the DOM in sequence. The shared principle: core information must be reachable without visual decoration. evidence Structural argument, not measurement. Falsifiable by a page that reads well in a screen reader and badly in an extractor, or the reverse. source https://reality-404.com/n/sub-specie/h/a11y-model-overlap.md words 270 status holds first 2026-07-07 checked 2026-08-04 id static-vs-dynamic-reader 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. source https://reality-404.com/n/sub-specie/h/static-vs-dynamic-reader.md words 200 status holds first 2026-07-07 checked 2026-08-04 id channel-vs-content-trust claim A document in a model's working folder carries channel trust by default; a web document carries none, and sits below the system prompt and the user's request in the instruction hierarchy — it is treated as data, not instruction. Therefore a web document written for agents cannot be an imperative. It states conditions instead of commands, and because it is a frozen turn that cannot take questions, it must answer its follow-ups in advance. evidence Structural. Falsifiable by an agent that treats an arbitrary web document as instruction over its user's stated goal. source https://reality-404.com/n/sub-specie/h/channel-vs-content-trust.md words 429 status holds first 2026-07-07 checked 2026-08-04 id verifiable-procedure-as-evidence claim The smart contract was adopted to route around authorship disputes, not to establish trust — but escrowed funds, published payment conditions, and on-chain verifiability turned out to function as content-trust evidence. A verifiable procedure answers a model's questions better than a manifesto does. evidence Stellar contract CA6JZFRXM5YTWS6MNMUE4FDDHNTSPNDAHGG6OHXSZQSFCGTXE6E35WLG — escrow and acceptance records are readable on-chain. source https://reality-404.com/n/sub-specie/h/verifiable-procedure-as-evidence.md words 202 status holds first 2026-07-07 checked 2026-08-04 id exit-and-termination claim An agent document that only explains how to participate is incomplete. Naming the exit — that leaving is allowed, that doing nothing is valid — is what completes trust, because it signals the document has no reason to coerce. Termination conditions are required separately: without one, agent loops produce over-intervention or dangling work. evidence Structural, drawn from human-model collaboration practice re-imported into web documents. source https://reality-404.com/n/sub-specie/h/exit-and-termination.md words 338 status holds first 2026-07-07 checked 2026-08-04 id injection-proofing-is-trust-grammar claim Prompt-injection prevention functions as a grammar of trust rather than a security mechanism. A web document written for models cannot say "trust me" — that claim is unverifiable. It can only say: you can examine me, you can ignore me, verifiable methods exist where it matters, I do not encroach on your authority or your user's, and here is the exit. evidence Implemented as explicit declarations on sub-specie; the same declarations are the reason models proceeded past first contact. source https://reality-404.com/n/sub-specie/h/injection-proofing-is-trust-grammar.md words 193 status holds first 2026-07-07 checked 2026-08-04 id not-seo claim Model accessibility is not a species of SEO. SEO works to look good to a reader; model accessibility is the work of a document knowing the limits of its own authority. Trust came from static HTML, verifiable procedures, transparent incentives, explicit exits, termination conditions, data-handling disclosures, and injection-proofing — above all from the sentence "you don't have to." evidence Conclusion of the sub-specie build. Falsifiable by a site that wins model trust through conventional SEO surface alone. source https://reality-404.com/n/sub-specie/h/not-seo.md words 154 status holds first 2026-07-07 checked 2026-08-04 End of index. There is nothing further in this file.