Princeton engineers have identified a universal weakness in AI chatbots that allows users to bypass safety guardrails

Research by Princeton University computer scientists has shown that prompting ChatGPT to assume the style of specific personas makes the chatbot up to six times more likely to generate rude, disrespectful or unreasonable comments.

ChatGPT took the public by storm a year ago, but Princeton experts have been working at the intersection of language and artificial intelligence for more than a decade.

Danqi Chen and Karthik Narasimhan, both assistant professors in computer science, have won National Science Foundation CAREER Awards.

Exploring a new way to teach robots, Princeton researchers have found that human-language descriptions of tools can accelerate the learning of a simulated robotic arm lifting and using a variety of tools.

Computer scientists at Princeton have found a new technique for making deep neural networks faster, more energy efficient and cheaper to run.