AI Safety Newsletter #13

Welcome to the AI Safety Newsletter by the Center for AI Safety. We discuss developments in AI and AI safety. No technical background required. In this story, we discuss a recent paper on why proxy goals fail. First, we introduce proxy gaming, and then summarize the paper’s findings. Proxy gaming is a well-documented failure mode in AI safety. For example, social media platforms use AI systems to recommend content to users. These systems are sometimes built to maximize the amount of time a user spends on the platform. The idea is that the time the user spends on the platform approximates the quality of the content being recommended. However, a user might spend even more time on a platform because they’re responding to an enraging post or interacting with a conspiracy theory. Recommender systems learn to game the proxy that they’re given. When the proxy no longer approximates the goal, the proxy has failed. However, proxy gaming isn’t observed only in AI systems. In economics, it’s know

Welcome to the AI Safety Newsletter by the Center for AI Safety. We discuss developments in AI and AI safety. No technical background required. In this story, we discuss a recent paper on why proxy goals fail. First, we introduce proxy gaming, and then summarize the paper’s findings. Proxy gaming is a well-documented failure mode in AI safety. For example, social media platforms use AI systems to recommend content to users. These systems are sometimes built to maximize the amount of time a user spends on the platform. The idea is that the time the user spends on the platform approximates the q