Coping with AI Advancements and Availability
With the widespread availability of Artificial Intelligence (AI) through tools like ChatGPT, there is an equally widespread availability of AI checkers. It can be difficult to sift through what to do with such a proliferation of new technology, especially when it has such direct implications for higher education. This feature gives an overview of AI generator technology and briefly investigates the reliability of current AI generation detection tools.
Conversations surrounding AI generators
The recent proliferation of artificially intelligent chatbots that enable users to produce text based on prompts that dictate length, format, style, level of detail, and language have sparked many recent conversations in higher education circles. Here at Ohio State, many of our partners in teaching and learning have already released formal statements and assistive content on the subject. If you are not familiar with these items, we encourage you to explore these statements and resources using the links below:
Prepared Statement
Teaching and Learning Guides
Many of the conversations pertaining to AI generators surround what can be done to reliably detect when these tools have been or are being used. ASC ODE has explored some considerations surrounding these questions to help faculty imagine the future of these tools for teaching and understand their current limitations, the findings of which are shared below.
Detecting AI generated text
One of the most pressing concerns that people have raised regarding AI-generated texts in the context of higher education is the implications it poses for academic integrity. Because widespread use of AI-generated content is an emergent issue, AI detection software is popping up as quickly as AI-generating software and both are, ironically, heavily reliant on AI programming to learn and process text and commands. Thus, it is difficult to trust the reliability of some of these tools and know with confidence if something is AI-generated.
As a part of our investigation, ASC ODE experimented with AI detectors and ran the same text through three different free programs. The text we used was AI generated using the OpenAI chatbot, ChatGPT, based on the prompt, “describe in detail the challenges and benefits of using AI in higher education.” The text that ChatGPT produced was as follows, with only the formatting altered to increase accessibility:
