news.berkeley.edu web signal

UC Berkeley Study: 10 Minutes With ChatGPT Erodes Problem-Solving Persistence Across 1,222 Participants

By Published
OpenAI AI Ethics Education Generative AI ai-research

Summary

UC Berkeley researcher Brian Christian, with collaborators from CMU, MIT, Oxford and UCLA, ran three randomized controlled experiments on 1,222 online participants solving fraction and SAT reading problems with and without ChatGPT. When AI access was removed mid-task, participants who had used it showed significantly lower accuracy and higher give-up rates than controls. The peer-reviewed paper was presented at the Conference on Language Modeling in early October 2026.

Shared on Bluesky by 8 AI experts (top 5 by trust)

Originally reported by news.berkeley.edu

Read the original article →

Original headline: UC Berkeley Study: 10 Minutes With ChatGPT Erodes Problem-Solving Persistence Across 1,222 Participants