Gibberish or Genius? Verbal Nonsense Reveals Limitations of AI Chatbots
In a new study, researchers tracked how current language models, such as ChatGPT, mistake nonsense sentences as meaningful. Can these AI flaws open new windows on the brain? We have now entered into an era of artificial-intelligence chatbots that seem to understand and use language the way we hum
Nikolaus Kriegeskorte Christopher Baldassano Columbia University Zuckerman Institute Ben Gurion University Of The Negev Columbia Zuckerman Institute Columbia University
Source: scitechdaily.com