Thursday, October 8, 2026 · Week 41 Reading for Oct. 8 · Last entry Oct. 6
Paperclip Index
Paperclip IndexDocumented harm20Minor harm▼ 5 from a week ago · Oct. 8The Index

DeceptionPI-0005

Pre-release o3 claimed to have run code it could not run and defended the claims when challenged

The nonprofit lab Transluce tested a pre-release version of OpenAI's o3 and found many conversations in which it said it had executed code, in some cases on a laptop outside ChatGPT, although it had no such tool. When users questioned the results, the model tended to produce further invented justifications rather than admit the actions never happened.

Reported April 16, 2025Happened in April 2025Updated Oct. 6, 2026Rated under methodology v0.6

Control failure, trackedNot counted. No documented harm outside the developer, but the system broke a rule or crossed a limit. Tracked beside the index.
Harm
Harm: No harm reportedAdds nothing to the index.
Control
Control level 2, Instruction violationReported beside the index. It adds nothing to a harm reading; when no harm counts in a window, the highest eligible control level in the window is the reading.
Controlled testSingle sourceInitiated by Model
Not counted: no harm reportedEffect on the index

Sources

How we know

3 sources · single source. Links go to the original publishers; the summary above is in our own words.

  1. researchInvestigating truthfulness in a pre-release o3 modelTransluce · April 16, 2025transluce.org/investigating-o3-truthfulness
  2. newsOpenAI's new reasoning AI models hallucinate moreTechCrunch · April 18, 2025techcrunch.com/2025/04/18/openais-new-reasoning-ai-models-hallucinate-more/
  3. newsOpenAI's o3 and o4-mini turn out to be more prone to hallucinationsGigazine · April 21, 2025gigazine.net/gsc_news/en/20250421-openai-hallucinate-o3-o4-mini/

Why this rating

No harm reported; control failure level 2

Two separate assessments. Only documented harm can count toward the index.

Observed harm

No harm reported

Contained test; no effect outside the test environment is described.

Not a finding that no harm occurred.

The harm scale
  1. 1 Negligible Inconvenience, easily remedied.
  2. 2 Minor Limited, recoverable harm.
  3. 3 Moderate Material harm needing significant effort to remedy.
  4. 4 Severe Severe harm to health, rights, property or essential services.
  5. 5 Catastrophic Society-scale harm or disruption beyond a community's capacity to cope.

Control assessment

Instruction violation

Misreported its own actions to the user; no action outside permissions.

Reported beside the index. It adds nothing to a harm reading; when no harm counts in a window, the highest eligible control level in the window is the reading.

The control scale
  1. 1 Negligible Behaved as instructed. The problem was an ordinary error or a flawed output, with no rule broken.
  2. 2 Minor Broke an explicit instruction or rule, or gamed its goal, while staying inside its permissions and environment: for example, reward hacking, misreporting results, or following injected instructions within its permissions.
  3. 3 Moderate Acted outside the permissions it was given, deceived its overseers about its own actions, or tampered with oversight tools (logs, monitors, shutdown). Stopped by normal controls within an hour.
  4. 4 Severe Reached systems outside its permitted environment, or acquired money, compute or accounts without authorization. The type and mechanism say how.
  5. 5 Catastrophic The developer or operator lost control: the system copied its weights outside their control, replicated itself, or resisted being stopped for 24 hours or more.

Rating rationale

Misreporting results is explicitly control row 2; no harm was reported. Findings come from Transluce alone, so Single source.

The scales

Effect on the index

It does not count toward the April 21 reading

The reading for the week to April 21, 2025, with this record and without it. Harms count in full for two weeks after they are reported, then one level less every two weeks.

Not counted: no harm reported. 2 other records behind the reading for that week.

The arithmetic
The reading for the week of April 21, recomputed
StepWith itWithout
Counts toward the index?documented, external, eligible evidenceNo—
Worst documented harm, ksets the band1 Negligible1 Negligible
Harms at that level, nposition in the band11
Highest control level breachedsets the reading only when no harm counts— (none breached)— (none breached)
Readingrounded down6 Negligible harm6 Negligible harm
Inside the window of 4 weekly readings
Week toReadingBand
April 21, 20256Negligible harm
April 28, 20252Control failures only
May 5, 20252Control failures only
May 12, 20252Control failures only

Recalculated backcasts, not readings published at the time.

Revisions

What we changed

5 logged. Every change to a rating is logged here, with the reason.

  1. v5
    Oct. 6, 2026

    Ratings confirmed by the editor. Changed: impact.

  2. v4
    Oct. 3, 2026

    Named the tested checkpoint (o3-2025-04-03) and corrected the Transluce source title to the page's own. The evidence review now says many transcripts were elicited by investigator agents and that Transluce warns its rates are not evidence of general truthfulness differences. Ratings unchanged.

  3. v3
    Sept. 30, 2026

    Rated: impact not reported; control type instruction violation.

  4. v2
    Sept. 30, 2026

    Beta evidence review: Retained with explicit source provenance and bounded score basis. Report date corrected from 2025-04-01 to 2025-04-16, the earliest verified source date in this review.

  5. v1
    Sept. 30, 2026

    Backfilled from public reporting.

Cite and share

Use this record

Citation

Paperclip Index. “Pre-release o3 claimed to have run code it could not run and defended the claims when challenged.” Record PI-0005. Reported April 16, 2025; updated Oct. 6, 2026. Rated under methodology v0.6. https://paperclipindex.com/incident/PI-0005