4. Using AI tools in your studies

  When using AI tools, ethical and responsible use principles, such as transparency, privacy, academic integrity, and fairness should be considered. For more information please refer to Charles Sturt University’s Statement of Principles for the use of Artificial Intelligence. Have a question about the principles? Email academicquality@csu.edu.au.

Read Your guide to generative Artificial Intelligence (AI) for current information and advice regarding AI use in your studies and assessments.

Watch Using Generative AI Technology at Charles Sturt University (Zoom recording 13m38s). This video is an assistive tool for students studying at Charles Sturt University in relation to the ethical and appropriate use of generative AI technology.

 Software such as Grammarly can only be used in an assessment task if it is specifically approved in the Subject Outline. The use of software that is not specifically approved in the Subject Outline may constitute a breach of Charles Sturt’s Student Misconduct Rule 2020 and Academic Integrity Policy.

To get feedback with grammar, punctuation or strategies to write more clearly, submit a draft of your assignment to Studiosity.

Generative AI, such as ChatGPT, has limitations:

• Recency Limit: ChatGPT’s knowledge is up to a specific cutoff date, meaning it won’t have information on events or developments that occurred after that date.
• Accuracy Limitations: ChatGPT can sometimes provide incorrect or misleading information.
• Contextual Understanding: ChatGPT may not fully grasp the context or nuances of certain questions or topics, leading to less relevant responses.
• Depth of Knowledge: For highly specialized or niche topics, ChatGPT might not have as detailed information as a domain expert would.
• Subjectivity and Bias: ChatGPT’s responses can inadvertently reflect biases present in the data it was trained on.
• Creative Content: ChatGPT might struggle with generating accurate and reliable information in creative or abstract contexts.
• Personalization: It cannot access personal data unless explicitly provided during the conversation, limiting personalized advice or information.
• Verification and Sources: ChatGPT cannot browse the internet or access real-time data, making it important to verify current facts and figures from reliable sources.

Source: Answer provided by OpenAI’s ChatGPT version 4 on 8 February 2024.

Comparison of information provided by the freely available ChatGPT 3.5 and subscription version ChatGPT 4, responses collected 8 Feb 2024:

Question: Who is the current British monarch?

ChatGPT 3.5 response: As of my last update in January 2022, the reigning British monarch was Queen Elizabeth II. However, there might have been changes since then. Please verify with up-to-date sources for the current British monarch as my information might be outdated.

ChatGPT 4 response: As of my last update in April 2023, King Charles III is the current British monarch, having ascended to the throne following the passing of Queen Elizabeth II on September 8, 2022.

Get started with Microsoft Copilot for Microsoft 365

What are recommendations for how to ask questions of Chatgpt?

Here are some recommendations for asking questions of ChatGPT:

• Be specific: The more specific your question is, the more accurate the response will be. Avoid asking open-ended questions that can have multiple answers.
• Use proper grammar and punctuation: ChatGPT is a language model and performs best when it is given well-formed sentences.
• Provide context: If your question is related to a specific topic or field, provide some context to help ChatGPT understand the question better.
• Be concise: Keep your question short and to the point. Long and complex sentences can be difficult for ChatGPT to understand.
• Avoid asking personal information: ChatGPT is a machine learning model and it does not have personal information. It also has a knowledge cut-off so it might not have the most recent data.
• Be patient: ChatGPT is a large model and it can take a moment to generate a response.
• Be aware of its limitations: ChatGPT is a model trained on a large dataset of text, so it may not have knowledge of certain information or events that have occurred after its knowledge cut-off date. It might also struggle with certain types of questions, like understanding sarcasm or idiomatic expressions.

Can Chatgpt provide information about authoritative sources for different study topics?

ChatGPT has access to a vast amount of information and can certainly provide information about authoritative sources for different study topics. However, it is important to note that not all the information provided by the model may be accurate or up-to-date. It is always a good idea to verify any information provided by ChatGPT with multiple sources and to consider the credibility of the source before using it for research or academic purposes.

To find authoritative sources, you can ask ChatGPT for things like:

• Can you give me some reputable sources for information on [topic]?
• What are some well-known journals or books on [topic]?
• Who are some experts or researchers in the field of [topic]?

Is ChatGPT able to critically analyse information?

ChatGPT can generate responses based on patterns and associations it has learned from the text it has been trained on, but it cannot understand the meaning or context of the information it is processing. Therefore, it cannot make judgments about the accuracy or reliability of the information it is providing.

It’s also good to keep in mind that the information is generated based on the data it was trained on, which might contain biases and inaccuracies.

It’s a good practice to cross-check the information provided by ChatGPT with credible sources before making any decision or taking any action.