ChatGPT can write code, plan a travel itinerary, and even produce a Shakespeare-inspired play, but does it know how to make a simple cup of coffee when you ask it to? The Coffee Test, attributed to Steve Wozniak, Apple co-founder, is an experiment that lets one assess the intelligence of an AI machine. The test requires an AI machine to: “…go into an average American household and figure out how to make coffee, including identifying the coffee machine, figuring out what the buttons do, finding the coffee cabinet, etc.”
The Coffee Test is an important benchmark for measuring an AI’s intelligence because making coffee is simple yet encapsulates the fundamentals of basic human function. Such human activity includes the ability to perceive and navigate a way in familiar environments (e.g., a house), having ‘common sense’ reason to correctly deduce that coffee powder would be located in a cupboard, and having knowledge of the steps to boil water and brew coffee.
Jie Yee Ong (the Community Manager for The Chainsaw) is reporting and demonstrating (screenshots) her conversations with ChatGPT, trying to get Chat to make her a cup of coffee. “ChatGPT failed” concludes Jie Yee Ong: it answers the questions of “how to” well enough but keeps “standing its ground in refusing to labor” for her. It is, after all, a machine with no “making” capabilities.
Chris Rourk in Medium explains the “Coffee Test,” as proposed by Steve Wozniak, would require a robot – not a computer screen. That’s another way of looking at this test, considered for artificial general intelligence (AGI.)
