Welcome to the Current Capabilities and Limitations page. This will provide you with a starting point to explore further discussions on the capabilities and limitations of GenAI tools. 

GenAI tools continue to improve as they train which means that their capabilities and limitations will change over time and may vary from tool to tool depending on how it was trained. During this project, several key capabilities and limitations of ChatGPT emerged.

Please explore the links below to find specific information you are looking for on this page.

Capabilities

• Produces easy to understand text in plain English
• Produces grammatically correct and generally well-structured text
• Summarises or distils key points from a text
• Solves math problems
• Writes code
• With plug-ins, can generate graphs/charts/images
• Brainstorms ideas
• Converses with the user and answers questions

Limitations

• Hallucinations (inaccurate or made-up information)
• Biases based on training data
• Produces surface-level or general information (not capable of critical analysis)
• Cannot provide citations or references (or produces fake ones)
• Struggles to respond to specific word count requests
• Does not always respond to prompts accurately and can require several specific prompts to refine to the desired output
• Limited to training data (many tools are only trained on data up to a certain date so are not aware of up-to-date or specific information)
• Code produced is accurate but is the most straightforward and basic version of the code so it is not robust or secure and would not stand up in many real-world applications