What are Chat GPT's Limitations?
ChatGPT’s response will vary. Any differences in prompts, or even iterations of the same prompt can produce different responses.
ChatGPT sometimes produces responses that are factually incorrect or biased, and cite non-existent or incorrectly labeled sources, called hallucinations.
ChatGPT’s archive does not contain information about recent developments or current events, as there is at least a one year gap between the present and the information it has been trained on.
There are various forms of ChatGPT. The free version is more limited than ChatGPT 3.5 and ChatGPT 4, both of which have access to the internet, and are paid.
Adapted from Chat GPT & Other Generative AI Software by OSU Institute for Teaching & Learning Excellence.
ChatGPT is just one example of Generative AI. There are many Generative AI models, including those that generate text, images, and even video.
The following section discusses ChatGPT, since it is the one that has been most prevalent in higher ed conversations. Scroll down or click HERE to learn about other forms of generative AI.
ChatGPT
GPT = Generative, Pre-trained Transformer
ChatGPT is a Large Language Model (LLM) chatbot, created by OpenAI, which responds to prompts with natural language. It is trained on massive data sets, and generates textual responses that mimic human conversation.
Where does the information come from?
ChatGPT was trained on a body of text which allows it to generate text in response to a prompt. Some partial lists of the training dataset exist, and ChatGPT will also provide a partial list when queried. However, the entire body of text that has trained ChatGPT is unknown.
When ChatGPT provides an answer to a question, it will not immediately provide a reference for where the information came from. This is because it is pulling predictive language from a wide variety of places, so the information usually doesn't come from a single source. Because of this, you typically cannot trace the response back to a single parent source or know where the information came from.
How current is the information?
As of February 23rd, 2024, the cutoff date for the data ChatGPT was trained on is January 2022. This means the tool has limited access to events and information more recent than that. ChatGPT is being updated regularly, so this may change. However, it is important to realize that the currency of the information provided by ChatGPT is lagging. This can impact information credibility, especially when dealing with a topic where the age of your information matters.
Some of the above has been adapted from AI, ChatGPT, and the Library Libguide by Amy Scheelke for Salt Lake Community College, which is licensed as CC BY-NC 4.0, except where otherwise noted.
LinkedIn Facebook Instagram