Taking the Intentional Stance Seriously: A Guide to Progress in Artificial IntelligenceFinding claims that researchers have made considerable progress in artificial
intelligence over the last several decades is easy. However, our everyday
interactions with cognitive systems quickly move from intriguing to
frustrating. The root of those frustrations rests in a mismatch between the
expectations we have due to our inherent, folk-psychological theories and the
real limitations we see in existing computer programs. To address the
discordance, we find ourselves building mental models of how each unique tool
works: how we address Apple's Siri may differ from how we address Amazon's
Alexa, the prompts that create striking images in Midjourney may produce
unsatisfactory renderings in OpenAI's DALL-E. Emphasizing intentionality in
research on cognitive systems provides a way to reduce these discrepancies,
bringing system behavior closer to folk psychology. This paper scrutinizes the
propositional attitude of intention to clarify this claim. That analysis is
joined with broad methodological suggestions informed by recent practices
within large-scale research programs. The overall goal is to identify a novel
approach for measuring and making progress in artificial intelligence.
arxiv.org