Position Paper: Bounded Alignment: What (Not) To Expect From AGI Agents
Addresses AI safety and risk for policymakers and researchers by advocating a shift in perspective, but is incremental as it builds on existing alignment discussions.
The paper argues that current AGI safety expectations need to evolve by incorporating insights from human and animal intelligence to foster more realistic views and better policies.
The issues of AI risk and AI safety are becoming critical as the prospect of artificial general intelligence (AGI) looms larger. The emergence of extremely large and capable generative models has led to alarming predictions and created a stir from boardrooms to legislatures. As a result, AI alignment has emerged as one of the most important areas in AI research. The goal of this position paper is to argue that the currently dominant vision of AGI in the AI and machine learning (AI/ML) community needs to evolve, and that expectations and metrics for its safety must be informed much more by our understanding of the only existing instance of general intelligence, i.e., the intelligence found in animals, and especially in humans. This change in perspective will lead to a more realistic view of the technology, and allow for better policy decisions.