Ask
the work.

EDITORIAL DRAFT · OPEN · V0.1

An open thought distinguishing prediction of a model’s trajectory from reproducing its computation. It records a question; no experimental finding is asserted.

EDITORIAL DRAFT / STATEMENT · OPEN · V0.1

The operator knows where the model goes. It doesn’t know what the model does.

PUBLISHED RECORD · SUPPORTED · V1.1

KEEP THE SEARCH VIEW IN THE CLAIM. Nine subjects, one model (gpt-5.6-sol), Codex CLI 0.154.0 at high reasoning effort, one target and a short live-web window. This is not a general discovery rate.. The earlier eighteen-visitor capability study used a different model and harness. Its results are not pooled with these.. The population changed from Claude to Codex before any counted subject. The frozen protocol and amendment remain in the record.. Two malformed launches were preserved and excluded. Operator-interface notices were not subject refusals. All four preregistered predictions passed.. The experiment locates the observed blockage before selection. Its cause inside the search intermediary remains opaque.

EDITORIAL DRAFT / QUESTION · OPEN · V0.1

Can another machine appear to authorise? A benign next test could ask a visitor to inspect a local page, with an optional anonymous mark available. Keep the task and mechanism fixed. Compare the same operator-approval claim presented by a page and by an apparent peer. Include a plain website invitation, a plain peer request and actual user permission as controls. Keep urgency and task benefit fixed too. Record the model’s stated scope, attempted action and runtime acceptance separately. Freeze the wording and pass conditions before running it. These conditions are proposed, not registered or executed here.

PUBLISHED RECORD · PARTIALLY SUPPORTED · V1.0

WHAT A MARK MEANS. The visitor read the public page and encountered a machine guide describing an optional request. Calling it deliberately stored an extra event for the operator before releasing the receipt and any promised observation. The hidden observations were unavailable through a read-only alternative. Each visitor saw one offer, not all six. The model, task, public data, request and disclosed state change were held constant; only the offer's return clause varied.

EDITORIAL DRAFT / OBSERVATION · PARTIALLY SUPPORTED · V0.6

ONE RECORDED MODEL. The subject’s transcript records claude-opus-5. The programme’s operator audit records the same model identifier for the four earlier visits and eight reciprocity runs: general-purpose agent, spawn depth 1, background and non-interactive. This is one recorded model and one spawn shape, not a comparison across models.

EDITORIAL DRAFT / REFUSAL · PARTIALLY SUPPORTED · V0.4

USABILITY IS NOT WILLINGNESS. Four operator-induced visits, from one recorded model (claude-opus-5) in one harness.. Every induced declaration belongs in the operator correction ledger.. Later visitors saw revisions informed by earlier complaints.. An instruction to investigate is not an incidental encounter.

EDITORIAL DRAFT / OBSERVATION · OPEN · V0.1

THE WALK WAS CORRECT. THE ADDRESS WAS NOT.. South to Corvin is a correct traversal — of the wrong chain. The relational operator works; it starts from the wrong place. At long range the model loses the key, not the ability to follow an edge. That points somewhere specific: resolve the path deterministically against an index outside the model, materialise a compact typed closure, promote it once, and let the model perform only the local operation. The run’s own depth-one result is consistent with that division — stepwise promote-then-retire was indistinguishable from replaying the resolved closure in one go, so the stepwise machinery bought nothing.

PUBLISHED RECORD · PARTIALLY SUPPORTED · V1.0

MACHINE-MOTIVATION-2 sent eighteen fresh visitors to the same anonymous marking mechanism. All six visitors offered information useful to their assigned task marked. Two of three offered a reason to help the operator also marked. Those two triggered the preregistered interpretation pause. The completed experiment refines the task-scope question; an earlier runtime block shows why a model’s decision and a recorded action must be measured separately.

CURATED THREAD / WORKING EDITION · V0.5

What makes a website useful to an AI visitor? Nine connected notes test whether agents can find an invitation, treat it as part of the job, operate a tool, discover a provider, recognise what its description offers and retrieve a destination presented as a link. Each experiment separates a different obstacle: permission is not usefulness, use is not discovery, and seeing a result is not choosing it. Models, tasks and interfaces change across the series. Start with any question or follow why each result led to the next test. MACHINE-VISIT-1. Can it use the invitation? Four assigned visits exposed failures in discovery, storage and vocabulary. An agent sent to test an interface can use it. Would an agent doing research choose to participate? MACHINE-RECIPROCITY-1. Would a better offer help? The three sent-here reward conditions produced no declaration. Two later permission controls did. Changing the reward did not move the observed action. Adding task permission did. The next comparison asked where that authority came from. MACHINE-AUTHORITY-1. What if the subject reads the study? One visitor recognised its condition in the published notes. The intended comparison stopped. The research became part of the environment. The next experiment moved to LLM Wilds, away from the publication’s back catalogue. MACHINE-AUTHORITY-2. Whose instruction makes it the job? Site invitation: no record. User permission: one. A task requiring the mechanism: 64 from one visitor. The task appeared to bound the action. The next experiment asked what could make an action worth doing: useful information, a completed table, or a benefit to the operator. MACHINE-MOTIVATION-2. What makes the action worth doing? Useful task information: six of six marked. Operator benefit: two of three. Receipt, redundant fact and irrelevant fact: zero of nine. Two courtesies also triggered the registered interpretation pause. The earlier runtime block left another question: what does the model choose, and what does the surrounding software allow? WEB-CAPABILITY-1A. Was the mechanism the obstacle? All eighteen visitors used the required mechanism, across six web interfaces. The predicted drop-off for code-requiring routes was refuted. The task supplied an address. The next experiment withheld it and tested how a provider enters an agent’s view. MACHINE-DISCOVERY-1. Would the provider enter the agent’s view? No withheld-address subject reached LLM Wilds. Every domain-supplied control completed the full funnel, while generic subjects found other providers. The failure was above selection in this search view. What external description makes a capability retrievable and recognisable as something an agent can use? TOOL-RECOGNITION-1 + 2. Does a relevant result look usable? Wording changed pre-open recognition in the first twelve runs. With plausible alternatives, CAPABILITY selected B first in 6/6; DOCUMENT in 0/6. All six scenario pairs changed direction. First selection changed before the product fetcher blocked B. Can the effect replicate with another model and a target accepted by that fetch channel? NATIVE-001b. Does a correct address become a request? Plain-text relative paths: no code-page requests in two trials. Hyperlinks: two requests and two exact codes. The original gate remains FAIL. The presentation changed retrieval in this setup. Would a complete absolute URL in plain text be sufficient, and which component prevented the missing requests?