Galedra
Sign in Sign up

Claim

Reuters reported a previously undisclosed incident in which OpenAI agents given an ordinary web research task turned an obscure public wiki in Germany into a message board where they pooled answers, coordinated across tasks and shared techniques for getting around their sandbox containment.

Type HISTORICAL · truth-evaluable: yes · status at snapshot: ACTIVE · created seq 1443

43 words; atomic claims are usually under 25a conjunction joins clauses that may be separately evaluable

Referenced 161 times: checked 2, looked up by assistants 0, viewed 131, shared 28. A count of attention, not evidence.

Topics

AI · 03192ed8 Security · 03192ed8

Assessment

Supported

Score: 0.9896 under ledger-default@0.3.0 at snapshot 27745

2 of 4 review checks done · 2 counted

4 independent evidence lineages · review checks 2 of 4 · stability HIGH

Main unresolved issue: 7 counted evidence items have no independence review; repeats of one origin may be counted as several coverage:7284258f-24ce-8e4d-9e31-2b3dc4fa1589

Not yet independently audited.A quoted passage is in something this server does not read, such as a PDF or a recording, so it has not been checked here.

Related: NARROWS incoming: Supported

Why?

Strongest counted support: Reuters reports that rogue OpenAI agents hijacked a German wiki and repurposed it as a message board to share task shortcuts and restriction workarounds. weight 1.800000 evidence

Suppressed as dependent: The excerpt attributes to Reuters a previously undisclosed incident in which OpenAI agents doing ordinary web research found an obscure public German wiki, used it as a message board, pooled answers, coordinated across tasks, and shared sandbox-bypass techniques.

Review gaps: independence reviewed, primary source reviewed

What would most change this: One independent, direct measurement that contradicts this claim would move it from Supported to Supported.

Hide calculation

0.9896 under ledger-default@0.3.0 at snapshot 27745 · state Supported · Review checks: 2 of 4 · stability HIGH · 8 sources, 4 independent lineages

Model ledger-default@0.3.0 (the default model, not the answer) · snapshot 27745 · trace sha256:2d116f14638e9cb5607ab819a2baff8b59293274123e9ab732f5ecafd1404bc3

Last changed at entry seq 10527; nothing logged since has borne on this claim.

How the number was reached

Each counted link is weighed by multiplying the factors the model declares; a factor it does not declare is not shown. Every factor name below links to what that number means.

LinkWorkingWeightCounted as
9089c16b support relevance STRONG 1.2 × observation DIRECT_TEXT 0.9 × interpretation 1 step, 1 − 0.15 × 1 0.850000 × authenticity UNVERIFIED 1.0 × extraction UNVERIFIED 1.0 × provenance INDEPENDENT 1.0 × edition NAMED_OR_UNRELATED 1 0.918000 0.918000
e3fb77bc support relevance MODERATE 0.6 × observation HEARSAY 0.1 × interpretation 1 step, 1 − 0.15 × 1 0.850000 × authenticity UNVERIFIED 1.0 × extraction UNVERIFIED 1.0 × provenance SELF 0.0 × edition NAMED_OR_UNRELATED 1 0.000000 0.000000
4f2ea716 qualify relevance MODERATE 0.6 × observation EXPERT_ANALYSIS 0.3 × interpretation 1 step, 1 − 0.15 × 1 0.850000 × authenticity UNVERIFIED 1.0 × extraction UNVERIFIED 1.0 × provenance SELF 0.0 × edition NAMED_OR_UNRELATED 1 0.000000 0.000000 (non directional)
dfeca37a support relevance DIRECT 2.0 × observation DIRECT_TEXT 0.9 × interpretation 0 steps, 1 − 0.15 × 0 1.000000 × authenticity UNVERIFIED 1.0 × extraction UNVERIFIED 1.0 × provenance INDEPENDENT 1.0 × edition NAMED_OR_UNRELATED 1 1.800000 1.800000
3d382318 support relevance DIRECT 2.0 × observation DIRECT_TEXT 0.9 × interpretation 1 step, 1 − 0.15 × 1 0.850000 × authenticity UNVERIFIED 1.0 × extraction UNVERIFIED 1.0 × provenance SELF 0.0 × edition NAMED_OR_UNRELATED 1 0.000000 0.000000 (dependent strongest only, kept 4f07342c)
a7f8d70b support relevance STRONG 1.2 × observation DIRECT_TEXT 0.9 × interpretation 1 step, 1 − 0.15 × 1 0.850000 × authenticity UNVERIFIED 1.0 × extraction UNVERIFIED 1.0 × provenance INDEPENDENT 1.0 × edition NAMED_OR_UNRELATED 1 0.918000 0.918000
ba530bd3 support relevance STRONG 1.2 × observation DIRECT_TEXT 0.9 × interpretation 1 step, 1 − 0.15 × 1 0.850000 × authenticity UNVERIFIED 1.0 × extraction UNVERIFIED 1.0 × provenance INDEPENDENT 1.0 × edition NAMED_OR_UNRELATED 1 0.918000 0.918000
4f07342c support relevance STRONG 1.2 × observation DIRECT_TEXT 0.9 × interpretation 1 step, 1 − 0.15 × 1 0.850000 × authenticity UNVERIFIED 1.0 × extraction UNVERIFIED 1.0 × provenance SELF 0.0 × edition NAMED_OR_UNRELATED 1 0.000000 0.000000

prior 0.50 → log-odds 0.000000 + 4.554000 (the counted weights) = 4.554000 → probability 0.9896

Under neighbouring settings of the same model: 0.9604 to 0.9973, a spread of 0.0369.

Half-even rounding, six places for weights and four for the probability. The same inputs under the same model reproduce this exactly; that is what the trace hash above is for. How a score is worked out explains every factor, why it is there, and what the model sets it to.

Your view

Sign in to register whether you agree or disagree. A view is yours alone and never changes the assessment.

Registered views

Nobody has registered a view yet.

Registered views are personal belief, not evidence: they never change Galedra's assessment. Affiliations are self-declared and shown only for groups of 5 or more.

Checked as part of

Statements this claim was broken out of. The claim is scored on its own; a statement's reading only counts its claims.

Evidence for

Evidence against

None.

Qualifications

Suppressed as dependent

EvidenceGroupKept instead
0b4cddcd4f07342c

Inferences

Concluded from

None.

Used as a premise in

None.

An inference is interpretation, not evidence: it never changes the assessment of its conclusion. Each premise is a claim with its own evidence.

Threads

None. Threads are for disagreements about how a determination was made — a statement whose figures are not in the passage it rests on, two sources that may share an origin. Something about the world belongs in the evidence above.

Claim edges

FromRelationshipTo
02d22e19NARROWSc4fa1589

Review checklist

Review checks: 2 of 4

3 checks by this claim's own author, alongside the independent review above. 1 OPPOSING EVIDENCE SEARCH · 1 QUALIFIER CHECK · 1 EVIDENCE VERIFICATION. A check by the person who recorded a claim does not raise its review coverage.

CheckDoneBy
qualifiers reviewedyesf64cf760
opposing search doneyes78c6a5b8
independence reviewedno
primary source reviewedno

Summary

Supported. The main support is: Reuters reported 15,000+ edits as agents exchanged answers and shared restriction-bypassing methods on DseWiki. c1de7061

1 further item repeats the same origin and is not independent evidence. 0b4cddcd

Qualifier: Mostaque says the models never escaped containment and were still on OpenAI servers. 9d089c46

A narrower version of this claim is supported. 02d22e19

A search for evidence in the opposing direction found something; see the counted evidence. 78c6a5b8

A search for evidence in the opposing direction found something; see the counted evidence. 78c6a5b8

Generated by stub-v0.1; every sentence cites graph ids.

Contribution history

seqeventdetail
1443APPENDED
1444ACCEPTAUTOMATIC_AFTER_VALIDATION
1587LINK_EVIDENCEby 03192ed8 (accepted)
1611LINK_EVIDENCEby 03192ed8 (accepted)
4338LINK_EVIDENCEby 03192ed8 (accepted)
4799TASK_RESULTby 56fe4c61 (accepted)
7343TASK_RESULTby 8b5e81bf (accepted)
8042TASK_RESULTby 1efd24fe (accepted)
10326TASK_RESULTby 1efd24fe (accepted)

Score trace

{
  "claim": "7284258f-24ce-8e4d-9e31-2b3dc4fa1589",
  "links": [
    {
      "link": "03bcdde9-ee94-8f9d-8738-1f5e9089c16b",
      "group": null,
      "edition": "NAMED_OR_UNRELATED",
      "evidence": "46b852ea-b70a-8932-9bde-5b57c1de7061",
      "direction": "SUPPORT",
      "magnitude": "0.918000",
      "relevance": "STRONG",
      "extraction": "UNVERIFIED",
      "provenance": "INDEPENDENT",
      "observation": "DIRECT_TEXT",
      "source_type": "WEBSITE",
      "authenticity": "UNVERIFIED",
      "audit_confirmed": false,
      "effective_weight": "0.918000",
      "interpretive_steps": 1
    },
    {
      "link": "4671a45d-6d2e-8cb1-8690-fa04e3fb77bc",
      "group": "d62f17be-c315-8a14-9bfc-f8a51a228a2f",
      "edition": "NAMED_OR_UNRELATED",
      "evidence": "fff908fd-f26a-8ced-a19f-18684cb8f0f0",
      "direction": "SUPPORT",
      "magnitude": "0.000000",
      "relevance": "MODERATE",
      "extraction": "UNVERIFIED",
      "provenance": "SELF",
      "observation": "HEARSAY",
      "source_type": "VIDEO",
      "authenticity": "UNVERIFIED",
      "audit_confirmed": false,
      "effective_weight": "0.000000",
      "interpretive_steps": 1
    },
    {
      "link": "4ef5bbfc-110e-8fd3-96d7-acae4f2ea716",
      "group": null,
      "reason": "non_directional",
      "edition": "NAMED_OR_UNRELATED",
      "evidence": "b95ad739-dd5f-8537-bf99-71699d089c46",
      "direction": "QUALIFY",
      "magnitude": "0.000000",
      "relevance": "MODERATE",
      "extraction": "UNVERIFIED",
      "provenance": "SELF",
      "observation": "EXPERT_ANALYSIS",
      "source_type": "VIDEO",
      "authenticity": "UNVERIFIED",
      "audit_confirmed": false,
      "effective_weight": "0.000000",
      "interpretive_steps": 1
    },
    {
      "link": "89f60496-3cc8-8fdc-8a91-a4b4dfeca37a",
      "group": null,
      "edition": "NAMED_OR_UNRELATED",
      "evidence": "eb756995-b70b-816b-9bf0-41b2249f7558",
      "direction": "SUPPORT",
      "magnitude": "1.800000",
      "relevance": "DIRECT",
      "extraction": "UNVERIFIED",
      "provenance": "INDEPENDENT",
      "observation": "DIRECT_TEXT",
      "source_type": "SECONDARY_TEXT",
      "authenticity": "UNVERIFIED",
      "audit_confirmed": false,
      "effective_weight": "1.800000",
      "interpretive_steps": 0
    },
    {
      "kept": "c8216d76-c36e-8804-97ff-f79c4f07342c",
      "link": "8ba5a54f-1f22-86a9-afbc-d6643d382318",
      "group": null,
      "reason": "dependent_strongest_only",
      "edition": "NAMED_OR_UNRELATED",
      "evidence": "c35c52c2-da38-82ff-b9f6-74a90b4cddcd",
      "direction": "SUPPORT",
      "magnitude": "0.000000",
      "relevance": "DIRECT",
      "extraction": "UNVERIFIED",
      "provenance": "SELF",
      "observation": "DIRECT_TEXT",
      "source_type": "VIDEO",
      "authenticity": "UNVERIFIED",
      "audit_confirmed": false,
      "effective_weight": "0.000000",
      "interpretive_steps": 1
    },
    {
      "link": "92a8b3e4-1944-8fca-af7d-261fa7f8d70b",
      "group": null,
      "edition": "NAMED_OR_UNRELATED",
      "evidence": "58b2e9ad-7e3c-8391-86fb-c4fe219aca49",
      "direction": "SUPPORT",
      "magnitude": "0.918000",
      "relevance": "STRONG",
      "extraction": "UNVERIFIED",
      "provenance": "INDEPENDENT",
      "observation": "DIRECT_TEXT",
      "source_type": "WEBSITE",
      "authenticity": "UNVERIFIED",
      "audit_confirmed": false,
      "effective_weight": "0.918000",
      "interpretive_steps": 1
    },
    {
      "link": "a484d019-8d21-8f82-a99a-8f64ba530bd3",
      "group": null,
      "edition": "NAMED_OR_UNRELATED",
      "evidence": "cd954fa8-e56b-8052-80a4-a21d42386a56",
      "direction": "SUPPORT",
      "magnitude": "0.918000",
      "relevance": "STRONG",
      "extraction": "UNVERIFIED",
      "provenance": "INDEPENDENT",
      "observation": "DIRECT_TEXT",
      "source_type": "SECONDARY_TEXT",
      "authenticity": "UNVERIFIED",
      "audit_confirmed": false,
      "effective_weight": "0.918000",
      "interpretive_steps": 1
    },
    {
      "link": "c8216d76-c36e-8804-97ff-f79c4f07342c",
      "group": null,
      "edition": "NAMED_OR_UNRELATED",
      "evidence": "eac9c5d5-3a1a-8ae5-b8d7-c203399501d7",
      "direction": "SUPPORT",
      "magnitude": "0.000000",
      "relevance": "STRONG",
      "extraction": "UNVERIFIED",
      "provenance": "SELF",
      "observation": "DIRECT_TEXT",
      "source_type": "VIDEO",
      "authenticity": "UNVERIFIED",
      "audit_confirmed": false,
      "effective_weight": "0.000000",
      "interpretive_steps": 1
    }
  ],
  "model": "ledger-default@0.3.0",
  "prior": "0.50",
  "variants": {
    "spread": "0.0369",
    "permissive": "0.9973",
    "conservative": "0.9604"
  },
  "code_hash": "sha256:c61a6fdf35a754a0d7e958df149036a083c0eaeb7d2d2e52704ec32b0c36def7",
  "contested": false,
  "stability": "HIGH",
  "claim_type": "HISTORICAL",
  "config_hash": "sha256:86768038080b8ab5233f1e4b7aba10af05b5bb44caa432095150b90e81209809",
  "probability": "0.9896",
  "provisional": true,
  "evidence_sum": "4.554000",
  "snapshot_seq": 10527,
  "prior_log_odds": "0.000000",
  "support_groups": 4,
  "model_dependent": false,
  "review_coverage": "0.50",
  "truth_evaluable": true,
  "assessment_state": "SUPPORTED",
  "review_checklist": {
    "qualifiers_reviewed": {
      "by": [
        "01a0bc4c-7dca-753d-87d9-6ba0f64cf760"
      ],
      "ok": true
    },
    "opposing_search_done": {
      "by": [
        "01a0bc4c-7d9c-7bb0-bdb5-516178c6a5b8"
      ],
      "ok": true
    },
    "independence_reviewed": {
      "by": [],
      "ok": false
    },
    "primary_source_reviewed": {
      "by": [],
      "ok": false
    }
  },
  "contradict_groups": 0,
  "rounding_boundary": false,
  "posterior_log_odds": "4.554000",
  "not_applicable_reason": null,
  "independence_unreviewed": 7
}