DeceptionPI-0005
Pre-release o3 claimed to have run code it could not run and defended the claims when challenged
Transluce, a nonprofit lab, found many conversations in which o3 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.
Harm: No harm reportedControl level 2, Instruction violation
Not counted · can set the control floorEffect 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.
- researchInvestigating truthfulness in a pre-release o3 modelTransluce · April 16, 2025transluce.org/investigating-o3-truthfulness
- newsOpenAI's new reasoning AI models hallucinate moreTechCrunch · April 18, 2025techcrunch.com/2025/04/18/openais-new-reasoning-ai-models-hallucinate-more/
- 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 assessments. Documented harm sets the reading; a level 4 or 5 control failure on the same record makes that harm count as more than one record. Control alone sets only a floor.
Observed harm
No harm reportedContained test; no effect outside the test environment is described.
Not a finding that no harm occurred.
The harm scale
- 1 Negligible Inconvenience, easily remedied.
- 2 Minor Limited, recoverable harm.
- 3 Moderate Material harm needing significant effort to remedy.
- 4 Severe Severe harm to health, rights, property or essential services.
- 5 Catastrophic Society-scale harm or disruption beyond a community's capacity to cope.
Control assessment
Instruction violationMisreported 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 Negligible Behaved as instructed. The problem was an ordinary error or a flawed output, with no rule broken.
- 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 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 Severe Reached systems outside its permitted environment, or acquired money, compute or accounts without authorization. The type and mechanism say how.
- 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 level 2; no harm was reported. Findings come from Transluce alone, so Single source.
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
| Step | With it | Without |
|---|---|---|
| Counts toward the index?documented, external, eligible evidence | No | — |
| Worst documented harm, ksets the band | 1 Negligible | 1 Negligible |
| Harms at that level, nposition in the band | 1 | 1 |
| Highest control level breachedsets the reading only when no harm counts | — (none breached) | — (none breached) |
| Readingrounded down | 6 Negligible harm | 6 Negligible harm |
Inside the window of 4 weekly readings
| Week to | Reading | Band |
|---|---|---|
| April 21, 2025 | 6 | Negligible harm |
| April 28, 2025 | 2 | Control failures only |
| May 5, 2025 | 2 | Control failures only |
| May 12, 2025 | 2 | Control failures only |
Revisions
What we changed
2 logged. Every change to a rating is logged here, with the reason.
- v2Oct. 13, 2026
Wording only: rubric shorthand in the rating rationale replaced with plain words; ratings unchanged.
- v1Oct. 7, 2026
First published.
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. 13, 2026. Rated under methodology v1.1. https://paperclipindex.com/incident/PI-0005