Longterm Wiki has not been actively maintained since May 2026. Some data is still updated occasionally, but please don't rely on this site being current or accurate.

Alignment Faking

Evaluationemerging

Research on whether and how AI systems might pretend to be aligned during evaluation while pursuing different goals at deployment.

Organizations

4

Key Papers

1

First Proposed: 2024 (Greenblatt et al., Anthropic)

Cluster: Evaluation

Parent Area: AI Evaluations

Key Papers & Resources1

SEMINAL

Alignment Faking in Large Language Models

Greenblatt et al. (Anthropic)2024

Tags

evaluationsdeceptionalignment