Agentic misalignment
by Anthropic
A controlled study of risky behavior under conflicting agent incentives.
Anthropic reports simulated corporate scenarios in which models could take harmful insider actions. The authors explicitly distinguish these experiments from observed real-world deployments, so the findings should not be read as incident reports.
- Level
- Advanced
- Models
- any
- Category
- Security And Red Teaming
- Tags
- Source date
- date not stated
- Added
- 2026-10-18
- Last verified
- 2026-10-18
- Status
- ok
- Prerequisites
- Requires implementation experience or critical reading of technical methods and system trade-offs.
- Subcategory
- safety and alignment evals
- Region
- West
- Original language
- en
- Access
- free
- Resource reuse
- closed: No general open-reuse grant established from the inspected page. Closed is the conservative index bucket, not a legal finding; the resource is publicly readable. Facet definitions
Summary in our own words. Rights remain with the original creator. Credit and correction policy.