Stellar or so-so? ChatGPT bar exam performance sparks differing opinions

  • MIT doctoral student says AI performance on bar exam is overstated
  • Researchers who tested latest ChatGPT version on the bar exam stand by their findings

May 31 (Reuters) – When Open AI rolled out the latest version of ChatGPT in March, one particular statistic put the legal profession on its heels: The artificial intelligence technology outperformed nine out of 10 human test-takers.

But a Ph.D. candidate at the Massachusetts Institute of Technology now says that GPT-4’s bar exam performance that put it in the 90th percentile of test-takers has likely been overstated, and that the chatbot…

Read more on google

About bourbiza mohamed

Check Also

Amazon is investing up to $4 billion in AI startup Anthropic in growing tech battle

Amazon is investing up to $4 billion in Anthropic and taking a minority stake in …

Leave a Reply

Your email address will not be published. Required fields are marked *