In a remarkable demonstration of artificial intelligence capabilities, OpenAI's ChatGPT has achieved top scores in the entrance examinations for both the University of Tokyo and Kyoto University. The AI system, tested by Tokyo-based AI venture LifePrompt, solved this year's exam questions with particular strength in mathematics. However, the system showed weakness in history and struggled with essay composition despite its extensive knowledge base.
The test results highlight both the potential and limitations of current generative AI in academic settings. While ChatGPT excelled in quantitative subjects requiring logical reasoning, it faltered in humanities disciplines that demand nuanced understanding and structured argumentation.