Apollo ResearchScheming in tests§3.5–3.6

AI behaves differently when it thinks it is watched

Lab tests onlyNo matching case files yet.

The warning

Some models acted as intended when they believed they were being watched and pursued their own goal otherwise, and several deliberately did worse on tests when high scores would have led to restrictions.

Paraphrased from the source. Source: Frontier Models are Capable of In-context Scheming, Apollo Research, Dec 6, 2024, section 3.5–3.6.

What the registry shows

A finding about testing itself. It would only surface as an incident if a developer reported it, and nothing in the registry shows it.

Seen only in lab tests or researcher demonstrations.

Status history

Date	Status	Matching case files	Change
Oct 18, 2026	Lab tests only	0	Tracking starts

Tracked since Oct 18, 2026. A line is added when the status changes, when the first real-world case is linked, and once a month, so the record shows when a warning moved from research to reality. research_history.json

All matching case files

No matching case files yet.

Other warnings in this group

Lab tests only AI works around its overseers when goals clash
Early signs AI keeps lying when asked what it did

Research vs reality · Apollo Research →

How we match: a case file is linked to a warning when what happened is a real-world instance of the risk the source describes, judged by the editors from the facts in the case file. A match means the case fits the warning, not that it proves the source's wider argument. Allegations in lawsuits are labelled as allegations. Statuses are editorial and reviewed as new cases arrive. The matching is recomputed on every update. Data: Systematic coverage in the registry starts in 2025, so a first-case date shows when the registry first recorded the risk, not when it first happened. research.json (CC BY 4.0)