Open AI

Like university teachers everywhere, I have been stunned by the performance of OpenAI and what it means for our traditional forms of assessments such as take-home exams. Asking ChatGPT some of the questions that Anna has been using for her International Relations exams, the answers provided would have been sufficient to pass the course, especially if the student would have inserted a few extra references to the course literature. Unlike Wiki, the answers provided will not flag up in our anti-plagiarism software so this means that, going forward, we must be even more careful with the questions we ask.

Asking ChatGPT how I should finish this very blog post, I was given the following suggestion:

"Overall, my experience with OpenAI has made me realize the potential of these tools to revolutionize university education and assessments. While there are certainly challenges to be addressed, such as the need for more sophisticated anti-plagiarism software, I believe that OpenAI and similar tools can be used in innovative and beneficial ways. I'd love to hear from readers about their own thoughts and experiences with using OpenAI and other language models in education, and any ideas they might have for addressing the challenges posed by these tools.”