Stanford & Google’s fascinating research study: Exploring Unconventional AI Behaviour in a Virtual Town

Researchers let 25 AI bots loose in a virtual town. The results were fascinating

Researchers from Stanford University and Google released 25 AI-powered robots into a virtual city. They behaved more like people than you would expect.

As detailed in a recent, yet-to-be-peer-reviewed study, the researchers trained 25 different \”generative agents,\” using OpenAI’s GPT-3.5 large language model, to \”simulate believable human behavior\” such as cooking up breakfast, going to work, or practicing a specific profession like painting or writing.

The agents could hop from school to the cafe or bar after work in a virtual town named \”Smallville\”.

Source:
https://futurism.com/the-byte/bots-virtual-town

发表回复

您的邮箱地址不会被公开。 必填项已用 * 标注