Get the latest tech news

Advanced AI chatbots are less likely to admit they don’t have all the answers

Although AI models predictably get more accurate as they advance, they’re also more likely to (wrongly) answer questions beyond their capabilities rather than saying, “I don’t know.” That’s the conclusion from a team of AI researchers who analyzed chatbots from OpenAI and Meta.

“They are answering almost everything these days,” José Hernández-Orallo, professor at the Universitat Politecnica de Valencia, Spain, told Nature. “And that means more correct, but also more incorrect.” Hernández-Orallo, the project lead, worked on the study with his colleagues at the Valencian Research Institute for Artificial Intelligence in Spain. The data showed that the chatbots’ portion of wrong answers (instead of avoiding questions altogether) rose as the models grew.

Get the Android app