Since becoming widely available to the public last year, artificial-intelligence chatbots have dazzled people who experimented with them, kicked off a global development race and even contributed to the strike in Hollywood over their impact on writers and actors. AI tools have also generated fear that they will inexorably improve and threaten humanity. OpenAI’s ChatGPT debuted to the public in November, sparking the current frenzy, followed by Chat GPT-4 in March, meant to be more powerful than its predecessor. But new research released this week reveals a fundamental challenge of developing artificial intelligence: ChatGPT has become worse at performing certain basic math operations. The researchers at Stanford University and the University of California, Berkeley said the deterioration is an example of a phenomenon known to AI developers as drift, where attempts to improve one part of the enormously complex AI models make other parts of the models perform worse. “Changing it in one direction can worsen it in other directions,” said James Zou, a Stanford professor who is affiliated with the school’s AI lab and is one of the authors of the new research. “It makes it very challenging to consistently improve.”
Full research : ChatGPT 3.5 outperforms ChatGPT 4 in many tasks, including solving math problems, highlighting the issue of “drift” in improving AI models.