Principles for Embedded Evaluations
Apollo Research proposes principles for embedded third-party evaluations of frontier developers, verifying or falsifying safety claims about loss-of-control risks from scheming.
Research
Apollo Research
Understanding and evaluating deceptive AI. apolloresearch.ai
Focus All
Topic Lab practice + Evals
Source Apollo Research · 5
Date Any time
1 item
1 item
Embedded Evaluators are necessary for meaningful external testing
Apollo Research argues that final-checkpoint external testing is insufficient for catching internal-deployment risks and that meaningful external evaluation needs embedded evaluators with employee-level access.
1 item
A Loss of Control Threat Map for AI Research and Development
Presents a threat map tracing pathways from using AI to automate AI R&D toward loss of control, including misalignment passing across successive AI generations.
1 item
Precursory Capabilities: A Refinement to Pre-deployment Information Sharing and Tripwire Capabilities
Proposes "precursory capabilities" and a zoning taxonomy so pre-deployment information sharing and tripwire thresholds can flag frontier models approaching catastrophic-risk red lines.
1 item
The Evals Gap
Apollo Research argues that high-quality frontier-model safety evals are scarce and slow to build, and calls for more resources to close this "evals gap."