Common Generative AI Tools
With thousands of AI tools available it can be hard to know what tool to use and how to get started. Here we offer a general overview of popular tools for use in the post-secondary environment. Check back as we continue to update this page.
OpenAI’s ChatGPT has two versions: a free version using the foundational model GPT 4.0 or a paid version using foundational model GPT 4o with some added capabilities.
ChatGPT is a conversational chatbot that responds to a user’s prompt (or request) and can engage in continued dialogue to refine and improve responses.
The paid version also allows users to access “GPTs”. GPTs function as custom chatbots that can respond based on specific content you have shared with the GPT.
ChatGPT can interact with the internet, create images using Dalle3, interact with images, complete data analysis and work in voice-text, and text-voice.
There is a paid ChatGPT “Teams” that allows small sized teams to share a workspace and introduces additional data controls.
When using ChatGPT you can use “data controls” in your account settings to turn off the collection of your chat history.
You can see an overview of how to use ChatGPT in this video.
Microsoft’s Copilot uses both the foundational model GPT 4 and is free to access. McMaster has an enterprise wide license for Copilot for *faculty and staff* that means neither Microsoft or McMaster are collecting your prompt data.
Copilot interacts with the internet, can create images using Dalle3, completes data analysis and can interact with an open webpage. Like ChatGPT, Copilot is a conversational chatbot that responds to prompts and can further refine responses based on feedback.
More information on how to use Microsoft Copilot can be found at this link.
Google’s Gemini is another conversational chatbot that draws on Google’s large language model, Gemini.
Gemini interacts with the internet, can create images, text and code. Using Workspace, Gemini can also interact with Google products like Google Drive and Gmail.
Scite.ai is designed for citation analysis. It integrates machine learning and human input to provide a broader perspective on how publications are received and discussed within scholarly literature. It also includes a new feature called scite Assistant (in beta). Scite Assistant helps to answer questions with research backed information by using generative AI (Artificial Intelligence) to query the scite.ai citation index.
McMaster Libraries provides access to scite for current McMaster University students, faculty, and staff.
Capabilities/Features
- Scite.ai allows users to upload a manuscript and see if references have been retracted or heavily contrasted, find missing citations, or explore how others reference the same studies.
- Scite.ai facilitates more granular tracking of citation information by categorizing citations based on their contextual relevance to a cited work, classifying them as “supporting”, “mentioning”, or “contrasting”.
- Scite.ai facilitates more granular tracking of citation information by categorizing citations based on their contextual relevance to a cited work, classifying them as “supporting”, “mentioning”, or “contrasting” (known as Smart Citations). The Smart Citations API is integrated into the Lean Library browser extension and provides retraction information.
- Scite Assistant helps to combat the “hallucination” phenomenon wherein some generative AI tools produce citations that are nonexistent. It searches against full-text research articles and over 1.2 billion citation statements in scite.ai.
- Scite Assistant allows users to specify a response length for their query: short (100 – 200 words), medium (200 – 500 words), or long (500+ words).
- Scite Assistant can answer questions about a specific paper when the DOI (digital object identifier) is included in the search query.
- Scite Assistant provides users with the ability to enter a quote or use natural language in a search query to identify a specific source. This feature can be used to help verify information or fact check claims made on social media and elsewhere.
Limitations
- Scite.ai. includes limited grey literature, (e.g., no conference proceedings or dissertations), but does include books or book chapters when they have a DOI and preprints.
- Scite.ai’s reliance on DOIs means that articles without them, such as some older publications, might not be covered.
- Scite.ai’s accuracy in classifying citations can be low, particularly in distinguishing between the categories of “supporting” and “mentioning”.
- Scite Assistant may be limited in its ability to capture nuanced meanings, such as linguistic and cultural variations.
- Scite Assistant may cite a real reference in a way that does not reflect what the reference says.
- Scite Assistant tends to rely on a particular article in its response to a query, which could limit the scope of highlighted literature.
- Scite Assistant may provide inconsistent results to a query which raises concerns around reproducibility.
This tool overview by Ithaka S + R organizes generative AI tools into a table describing cost, capabilities, limitations and some commentary.
Prompting
Prompting refers to the process of providing an AI tool with a text-based input, or “prompt,” to guide its output generation. This is a foundational concept across various applications of generative AI, including text generation, image creation, music composition, and more. Understanding how to effectively craft prompts helps you get more useful outputs from the tools you are using. When prompting:
State the “role” and “goal” and “context”:
- Tell the AI tool what role you want it to assume (e.g. student, faculty member, trip planner, archivist, etc).
- Then tell it what goal or task you want it to complete. Use precise verbs like “summarize,” “explain,” “describe,” “create” to get better outputs.
- Finally add as much context as you can for the goal. Context can include the format, audience, tone and length of output, but can also include specific things you want the output to include or not include.
For example: You are a dietician [role]. Create a meal plan for the week [goal]. The meal plan should be in table format, include vegetables with every meal, not include any nuts, and be suitable for a family of four [context].
Then, iterate and refine: Rarely will your first prompt be perfect. Often, you’ll need to iterate on your prompt based on the outputs you receive. This iterative process involves refining your prompt to adjust the detail, style, or direction based on previous outcomes.
Finally, explore and experiment. Generative AI models, especially in creative tasks, can produce a wide range of outcomes from subtle changes in the prompt. This exploration can help you better understand the capabilities and limitations of the AI.
Prompt Libraries and Use Cases
Check out some of these “prompt libraries” for examples of prompts that may be useful for you.
More Useful Things Prompt Library from Dr. Ethan Mollick and Dr. Lilach Mollick