You can access Willamette's instance of Gemini by logging into Google with your Willamette account and navigating to gemini.google.com. If you are logged into Chrome with your Willamette account, you should not have to log into Gemini.
Google's statement about models and accuracy (located at the bottom of the screen):
Once you have entered a prompt into Gemini, you will see a window with your initial prompt at the top, Gemini's results below your prompt, and space for a new prompt below Gemini's results. The left sidebar of the window includes an icon for a new prompt (called "new chat"), a list of your recent prompts, which Gemini saves, and Gemini's user settings (at the bottom of the left sidebar.
(Right click on any of these screenshots to open them in a new tab or download them to see the image at a larger size).
You can add files to a prompt by clicking on the "+" icon in the prompt field. This gives you the option to add files from your computer or Google Drive. You can also click the microphone icon in the prompt box to speak your prompt to Gemini.
To look at the sources Gemini drew on to answer your prompt, scroll to the bottom of the prompt response and click the "Sources" button.
If you want to share your prompt results, click the share icon. You can export you results to Google Docs or as a Gmail email draft.
If you click on the hamburger icon, you can double-check the prompt response, copy the response, listen to it, or report a legal issue.
If you double-check your response, a message will appear at the bottom of the results saying "Check completed." A button saying "Understand the results" will appear. If you click on it, a pop-up box will appear to explain the results. You can also click the curled arrow icon to re-run your prompt through Gemini.
If you click the "Explore Gems" button in the left sidebar, you will see pre-made Gems. You can choose to use one of these, or create your own Gem to use with Gemini. Learn more about Gems in the Google Education file linked below the image.
When using generative AI tools, the better your prompts, the better the results you will get. En effective prompt not only sets the topic but also provides clear instructions on the task, effectively guiding the AI. Creating effective prompts can be a challenging task, as the quality of the output relies on the specificity and clarity of the prompts or input instructions.
Craft precise and unambiguous instructions. Specificity is key! The model will make an assumption on any point you don’t clearly explain.
Remember that as you chat with generative AI, the model will learn more about what you need. Use the conversational turns to help the AI improve its outputs. Also remember that simple prompts lead to simple answers.
A good prompt has 4 key elements: Role, Task, Requirements, and Instructions.
Prompts starting with "act as..." or "pretend to be..." will provide responses similar to that of the role which you provide. Setting a specific role for a given prompt increases the likelihood of more accurate information, when done appropriately.
The task is a summary of what you want the prompt to do. There is a lot of creativity that comes into writing a great task. It can range from generating birthday gift ideas to doing game show questions with the content from your last lecture.
Writing clear requirements is all about giving as much information as possible to ensure your response doesn't use any incorrect assumptions. AI models make assumptions for any information they don't have in the prompt.
Instructions will inform the AI how to complete the task. Instructions can include examples of how it is supposed to work, steps it can follow or any information.
The graphic prompt above was created by Lance Eaton