Subversion Strategy Eval: Evaluating AI's stateless strategic capabilities against control protocols
Mallen, Alex, Griffin, Charlie, Abate, Alessandro, Shlegeris, Buck
–arXiv.org Artificial Intelligence
AI control protocols are plans for usefully deploying AI systems in a way that is safe, even if the AI intends to subvert the protocol. Previous work evaluated protocols by subverting them with a human-AI red team, where an AI follows the human-written strategy. This paper investigates how well AI systems can generate and act on strategies for subverting control protocols whilst operating without private memory. Usually, decision-makers only need the ability to generate optimal plans. However, to subvert a protocol, an AI system must be able to reliably generate optimal plans in each context; coordinate plans with other instances of itself without communicating; and take actions with well-calibrated probabilities. We develop evaluations for a model's ability to generate subversion strategies and develop affordance experiments that help isolate component capabilities. Our initial evaluations with Claude-3.5-sonnet highlight reasons why statelessly strategizing to subvert control protocols might be hard. We hope that our work can serve as a starting point for evaluations aimed at assessing whether a model is capable of strategizing to subvert control protocols.
arXiv.org Artificial Intelligence
Dec-16-2024
- Genre:
- Research Report (1.00)
- Technology:
- Information Technology > Artificial Intelligence
- Applied AI (0.84)
- Machine Learning (1.00)
- Natural Language > Large Language Model (0.48)
- Representation & Reasoning (0.93)
- Information Technology > Artificial Intelligence