MIT AI Risk Repository · Risk Sub-Category · 54.03.03

Deceptive alignment

Category: Harm caused by unaligned competent systems

Description

"system learns to detect human monitoring and hides its undesirable properties—simply because any display of these properties is penalized by the feedback process, while that same feedback is usually imperfect. (Consider the problem of verifying a translation into a language you do not speak, or of checking a mathematical proof that is thousands of pages long.) [92, 259]. Rudimentary examples of deceptive alignment have been observed in current systems [322, 333]."

From Ten Hard Problems in Artificial Intelligence We Must Get Right (Leech2024 ), as extracted by the MIT AI Risk Repository (CC BY 4.0).

Classification

Causal entity
AI

Subdomain definition: AI systems that develop, access, or are provided with capabilities that increase their potential to cause mass harm through deception, weapons development and acquisition, persuasion and manipulation, political strategy, cyber-offense, AI development, situational awareness, and self-proliferation. These capabilities may cause mass harm due to malicious human actors, misaligned AI systems, or failure in the AI system.

How other frameworks describe this risk

Other entries from Leech2024