Building Safer AGI by introducing Artificial Stupidity
This addresses safety concerns for AGI developers and society by suggesting incremental modifications to existing AI systems to reduce risks.
The paper tackles the problem of making Artificial General Intelligence (AGI) safer by proposing the concept of Artificial Stupidity, which involves deliberately limiting AI capabilities to match human intellectual limits, and provides recommendations for implementing these limits based on a survey of human constraints.
Artificial Intelligence (AI) achieved super-human performance in a broad variety of domains. We say that an AI is made Artificially Stupid on a task when some limitations are deliberately introduced to match a human's ability to do the task. An Artificial General Intelligence (AGI) can be made safer by limiting its computing power and memory, or by introducing Artificial Stupidity on certain tasks. We survey human intellectual limits and give recommendations for which limits to implement in order to build a safe AGI.