He hopes that language-model-powered agents will be able to autonomously test software that taps into social connections before real humans use them. Large language models “have learned a heck of a lot about human behavior” from their copious training data, says Michael Bernstein, an associate professor at Stanford University who led the development of Smallville. It was fun to see them start talking to customers, taking naps, and in one case decide to start a podcast. The research shows how language models can be used to produce some fascinating and realistic, if rather simplistic, social behavior. The characters in this simulated world are powered by OpenAI’s GPT-4 language model, but the software needed to create and maintain them was open sourced by a team at Stanford University. The characters in the WIRED sim include Jennifer Moore, a 68-year-old watercolor painter who putters around the house most days Mei Lin, a professor who can often be found helping her kids with their homework and Tom Moreno, a cantankerous shopkeeper. The characters’ chat with one another and move around a map that looks a lot like the game Stardew Valley.
For the past few days, WIRED has been running a simulated society of 25 AI agents go about their daily lives in Smallville, a village with amenities including a college, stores, and a park.
You don’t have to be an MIT professor or a multinational company to get a collection of chatbots talking amongst themselves. Economist John Horton of MIT, for instance, sees potential in using these simulated humans-which he dubs Homo silicus-to simulate market behavior. The way language models seem to reflect human behavior has also caught the eye of some academics.
0 kommentar(er)
