Unleashing Sleeper Agents

Our project investigates the potential risks and implications of integrating multiple autonomous AI agents within national defense strategies, exploring whether these agents tend to escalate or deescalate conflict situations. Through a simulation that models real-world international relations scenarios, our preliminary results indicate that AI models exhibit a tendency to escalate conflicts, posing a significant threat to maintaining peace and preventing uncontrollable military confrontations. The experiment and subsequent evaluations are designed to reflect established international relations theories and frameworks, aiming to understand the implications of autonomous decision-making in military contexts comprehensively and unbiasedly.

We investigate the economic potential of Transformative AI, focusing on "temporal coherence"—the ability to maintain goal-directed behavior over time—as a critical, yet underexplored, factor in task automation. We argue that temporal coherence represents a significant bottleneck distinct from computational complexity. Using a Large Language Model to estimate the 'effective time' (a proxy for temporal coherence) needed for humans to complete remote O*NET tasks, the study reveals a non-linear link between AI coherence and automation potential. A key finding is that an 8-hour coherence capability could potentially automate around 80-84\% of the analyzed remote tasks.

We offer initial investigations into whether the untrusted model can 'simulate' the trusted monitor: is U able to successfully guess what suspicion score T will assign in the APPS setting? We also offer a clean, modular codebase which we hope can be used to streamline future research into this question.