Stay up to date on what's new in AI applications with these AI discovery tools.
Be Aware of Bias & Censorship
Generative AI is as biased as the human-generated content that it's trained on. Some developers have put strategies in place to prevent their AI products from producing clear-cut answers to controversial questions. It is currently impossible to fully eradicate bias from generative AI.
Develop Your Prompt Engineering Skills
To get the best results from employing the use of generative AI, your prompts should be clear and specific, and provide context for your question or request.
Use AI Ethically
If you use LLMs or other forms of generative AI for assistance with a project, be sure to cite and acknowledge your AI use. Always check with your instructor before using AI for help with a course project.
Disclosing AI use is an important element of ethical authorship practices. I used ChatGPT to help me with the structure of some content sections in this section of the guide.
The below selection provides a summary of a small number of popular LLMs.
Function (What is it? What does it do?): ChatGPT is an open source conversational AI chatbot developed by OpenAI. It is built from generative pre-trained transformer (GPT) models, a type of LLM.
Login (Does it require an account login?): Required
Cost: Freemium -- a free version is available, with fees required for extra features.
What sets it apart? ChatGPT is credited with the recent "AI boom," having prompted several other developers to release their own LLM chat bots in quick succession after its release. It is easy to use and has a wide range of applications. Chats are archived in the user's account for as long as the account exists. ChatGPT also enables users to share chats via public links.
Function: Claude is a conversational AI chatbot and text generator developed by Anthropic.
Cost: Freemium.
Login: Required
What sets it apart? Claude allows users to upload large text files, enabling them to analyze a text in various ways. Claude also puts a focus on privacy and ethical AI use. Chats are archived in the user's account for as long as the account exists.
Function: Gemini is Google's AI chatbot.
Cost: Freemium.
Login: Google/Gmail account required
What sets it apart? Unlike many of its competitors, the free version of Gemini is connected to the Internet, providing it with access to more up-to-date information. Gemini allows users to upload and analyze text, image, video, and voice files.
Function: Github's Copilot tool assists users with generating, updating, fixing, and understanding code.
Cost: Paid plans.
Login: Required
What sets it apart? While other LLMs can provide assistance with code, GitHub Copilot is specifically designed for this purpose and especially adept at it.
Function: Elicit is an LLM specifically designed to assist with academic research.
Cost: Freemium.
Login: Required
What sets it apart? Elicit is an academic research tool. It parses research inquiries and provides citations of relevant academic sources such as journal articles and books. It is also able to answer questions about these sources. Note: Elicit generally cannot help researchers find primary sources.
Function: Grammarly is designed to help with grammar, clarity, and writing style.
Cost: Freemium.
Login: Required
What sets it apart? Grammarly can help you polish your writing and avoid grammatical errors. Use it carefully, however—some plagiarism detection software may flag Grammarly-polished text as plagiarized.
Large language models (LLMs) are built on vast amounts of text data. They are trained to understand and generate human language and often take the form of conversational chat bots.
LLMs are powerful tools, but they have limitations. Users should understand what they can and cannot do in order to get the best results from their use. If you ask an LLM to do something it cannot do, it might tell you it doesn't know the answer to your question, but it's just as likely to hallucinate.
What are hallucinations? To put it simply, when a generative AI tool hallucinates, it makes up information that is false, misleading, or nonsensical. It presents this information as fact, so sometimes users don't realize that the output was a hallucination. You can avoid hallucinations by understanding LLMs' capabilities and adhering to the following guidelines:
Be aware that even when you follow the guidelines above, LLMs may hallucinate, make coding mistakes, or provide biased information. LLMs present hallucinated responses as fact. Always be critical of information you've received from an LLM.
The following tools for generating AI images and other media content are free or freely available to Merrimack students, faculty, and staff.
