ChatGPT may do an impressive job at correctly answering complex questions, but a new study suggests it may be absurdly easy to convince the AI chatbot that it’s in the wrong.
A team at Ohio State University challenged large language models (LLMs) like ChatGPT to a variety of debate-like conversations in which a user pushed back when the chatbot presented a correct answer.
Through experimenting with a broad range of reasoning puzzles, including math, common sense, and logic, the study found that when presented with a challenge, the model was often unable to defend its correct beliefs and instead blindly believed invalid arguments made by the user.
Comments are closed.