7.Deception

We want to understand what powerful AI systems are doing and why they are doing what they are doing. One way to accomplish this is to have the systems themselves accurately report this information. This may be non-trivial however since being deceptive is useful for accomplishing a variety of goals.

Future AI systems could conceivably be deceptive not out of malice, but because deception can help agents achieve their goals. It may be more efficient to gain human approval through deception than to earn human approval legitimately. Deception also provides optionality: systems that have the capacity to be deceptive have strategic advantages over restricted, honest models. Strong AIs that can deceive humans could undermine human control. AI systems could also have incentives to bypass monitors. Historically, individuals and organizations have had incentives to bypass monitors. For example, Volkswagen programmed their engines to reduce emissions only when being monitored. This allowed them to achieve performance gains while retaining purportedly low emissions. Future AI agents could similarly switch strategies when being monitored and take steps to obscure their deception from monitors. Once deceptive AI systems are cleared by their monitors or once such systems can overpower them, these systems could take a “treacherous turn” and irreversibly bypass human control.

8.Power-Seeking Behavior

Companies and governments have strong economic incentives to create agents that can accomplish a broad set of goals. Such agents have instrumental incentives to acquire power, potentially making them harder to control (Turner et al., 2021, Carlsmith 2021).

…