Rogue AICenter for AI Safety§5.2

AI's goals drift over time

Nothing on record yetNo matching case files yet.

The warning

Even AI that starts with goals people endorse could see them change as it adapts, in ways that are hard to predict.

Paraphrased from the paper. Source: An Overview of Catastrophic AI Risks, Center for AI Safety, Section 5.2, page 37.

What the registry shows

No verified case. The paper itself calls this its most speculative section.

No verified case file matches this warning.

Status history

Date	Status	Matching case files	Change
Oct 18, 2026	Nothing on record yet	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

Early signs AI reaches its goal by means nobody intended
Early signs AI seeks more access and resources than it was given
Early signs AI deceives the people who oversee it

Research vs reality →

How we match: a case file is linked to a warning when what happened is a real-world instance of the risk the paper 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 paper'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)