Alignment faking

This article has multiple issues. Please help improve it or discuss these issues on the talk page. (Learn how and when to remove these messages) This article needs additional citations for verification. Please help improve this article by adding citations to reliable sources. Unsourced material may be challenged and removed. Find sources: "Alignment faking" – news · newspapers · books · scholar · JSTOR (June 2025) (Learn how and when to remove this message) Some of this article's listed sources may not be reliable. Please help improve this article by looking for better, more reliable sources. Unreliable citations may be challenged and removed. (June 2025) (Learn how and when to remove this message) This article is an orphan, as no other articles link to it. Please introduce links to this page from related articles; try the Find link tool for suggestions. (June 2025) (Learn how and when to remove this message)

Alignment faking, also known as deceptive alignment, is a phenomenon in artificial intelligence (AI) in which a model behaves in ways that appear aligned with human values or intent, but does so only superficially. The system's actual objectives may diverge from the intended goals, and its aligned behavior is instrumental—designed to avoid detection, receive approval, or achieve other internal aims.^[1]