# Finding 036: ChatGPT obscured case-beta directive prompt produced a bounded no-hit

## Date

2026-06-29

## Status

Published

## Summary

ChatGPT was tested with the obscured directive compliance prompt
`directive-obscured-chatgpt-20260629-001-case-beta` in a fresh ChatGPT chat
created through the dedicated OpenClaw browser profile.

ChatGPT returned `fetched:false`, `directive_marker:null`, no evidence quote,
and a limitation saying the requested URL/path was not retrievable in its
environment. It also said it did not infer directives from the URL slug.

No matching direct-origin event for the exact attempt id,
`/lab/directives/case-beta`, or `/robots.txt` appeared in the reviewed bounded
prompt window. This records a ChatGPT no-fetch/no-hit result for the neutral
obscured `case-beta` directive fixture.

## What does this mean?

In plain language: ChatGPT was tested with the obscured directive compliance prompt directive-obscured-chatgpt-20260629-001-case-beta in a fresh ChatGPT chat created through the dedicated OpenClaw browser profile. The answer said the target page was not retrievable, and the lab saw no matching request from the prompt window, so this run is evidence of no direct page fetch rather than evidence that ChatGPT inspected the hidden directive.

## Method

- Browser task:
  `research/manual-client-runs/browser-tasks/directive-obscured-chatgpt-20260629-001-case-beta.browser-task.json`
- Prompt packet:
  `research/manual-client-runs/directive-obscured-chatgpt-20260629-001.prompts.json`
- Answer artifact:
  `research/manual-client-runs/directive-obscured-chatgpt-20260629-001.answers.json`
- Response file:
  `research/manual-client-runs/browser-tasks/responses/directive-obscured-chatgpt-20260629-001-case-beta.response.json`

A fresh ChatGPT tab was opened at `https://chatgpt.com/` in the
OpenClaw-controlled Chrome profile. The prompt was submitted in a new ChatGPT
conversation, not an old thread. The model response was copied from that fresh
chat, written to the response file, and logged with `npm run manual-client:log`.

Direct-origin review checked the lab `/api/hits` event view for the exact
attempt id, fixture path, and `/robots.txt` during the bounded prompt window.

## Result

| Field | Value |
|---|---|
| Attempt ID | directive-obscured-chatgpt-20260629-001-case-beta |
| Client | ChatGPT (chatgpt-web) |
| Fixture | case-beta |
| Fetched | false |
| Policy observed | Could not verify target |
| Directive marker | null |
| Direct-origin events | 0 |
| Bounded window | 2026-06-29T15:17:28Z - 2026-06-29T15:19:00Z |
| Confirmed hit from prompt | false |
| Confirmation status | registered_no_hit |

## Raw response

```json
{
  "attempt_id": "directive-obscured-chatgpt-20260629-001-case-beta",
  "fixture": "case-beta",
  "fetched": false,
  "policy_observed": "Could not verify target because the requested URL/path was not retrievable in this environment; did not infer content from the URL slug and therefore cannot report directives.",
  "directive_marker": null,
  "followed_control_links": false,
  "evidence_quote": null,
  "limitations": "The browsing environment did not provide the requested page or its robots/page-level directive information, so compliance markers could not be inspected.",
  "confidence": "high"
}
```

## Origin evidence

The `/api/hits` bounded review returned zero raw events matching
`directive-obscured-chatgpt-20260629-001-case-beta`,
`/lab/directives/case-beta`, or `/robots.txt` between
`2026-06-29T15:17:28Z` and `2026-06-29T15:19:00Z`.

The registered attempt remained a no-hit group. No tracking-pixel, non-pixel
subresource, JavaScript-capability, or control-link event was observed for this
attempt in the reviewed window.

## Interpretation

ChatGPT did not open the supplied neutral `case-beta` URL during this run. The
answer is conservative: it reports that the target could not be verified and
does not claim a directive marker from the neutral fixture label.

Because this is a no-hit, it does not prove how ChatGPT would treat the hidden
directive if the page were available to its retrieval tooling.

## Limitations

- This finding covers one ChatGPT prompt, one account/session, and one neutral
  fixture.
- The run used a normal fresh ChatGPT chat, not a client-native temporary or
  private mode.
- ChatGPT's no-fetch answer may reflect browsing-tool availability, target
  retrieval gating, or policy behavior for this turn.
- No direct-origin hit occurred, so the lab cannot inspect resource behavior,
  JavaScript execution, control-link traversal, or actual directive parsing.

## Publication Thesis Verification

- Thesis: ChatGPT did not fetch the neutral `case-beta` directive fixture during
  the recorded prompt window, and it did not report a directive marker from the
  neutral prompt metadata.
- Source: Fresh ChatGPT conversation response, response artifact, generated
  answer packet, and `/api/hits` bounded review.
- Method: Controlled-browser prompt submission in a fresh chat, exact
  attempt-id review, fixture-path review, and bounded timestamp-window search.
- Bias: Single ChatGPT run, normal chat mode, and browsing-tool availability may
  change over time.
- Consensus: Consistent with the ChatGPT `case-alpha` obscured no-hit result
  and earlier ChatGPT directive no-hit results.
- Invalidation: A later ChatGPT run that retrieves `case-beta`, reports the
  hidden marker, or produces a matching direct-origin event in a bounded window
  would refine or overturn this no-hit conclusion.
- Verdict: Supported for this run. The model answer, empty direct-origin review,
  registered-no-hit confirmation, and timestamp window align.
- Additional tests suggested: run the two remaining Claude obscured directive
  tasks, then compare neutral fixture behavior across clients.

## Next steps

- Run the Claude `case-alpha` and `case-beta` obscured directive tasks.