Summary
Gemini (formerly Google Bard), now powered by Gemini Pro, is a large language model (LLM) that can help users with a variety of tasks, including generating text and images, translating languages, answering questions, helping users learn a new skill, and writing different kinds of creative content
How to Obtain & Log in
Gemini is free, but it is currently in beta testing and it is available to a limited number of users. Please note: Gemini is not currently available in the UC Davis instance of Google Workspace.
You must be 18 or over and have a personal Google Account or a Google Workspace account for which your admin has enabled access to Gemini.
Features & Options
- Natural language understanding (NLU): Gemini can understand and respond to natural language prompts and questions. This means that you can interact with Gemini in the same way that you would with a human.
- Machine learning (ML): Gemini is powered by ML, which means that it is constantly learning and improving. As Gemini is exposed to more data, it becomes better at understanding and responding to your requests.
- Generative text and images: Gemini can generate images and different creative text formats of text content, like poems, code, scripts, musical pieces, emails, letters, etc.
- Information retrieval: Gemini can access and process information from the real world through Google Search. This means that Gemini can answer your questions in a comprehensive and informative way, even if they are open-ended, challenging, or strange.
- Multimodal search: Gemini can search for information across different modalities, such as text, images, and videos. This means that you can ask Gemini to find information about a specific image or video, or to translate text from one language to another.
Limitations
- Bias: Gemini is trained on a massive dataset of text and code, which may contain biased information. This could lead Gemini to generate biased responses, especially when asked about sensitive topics.
- Inaccuracy: Gemini is not perfect and can sometimes generate inaccurate information. It is important to fact-check any information generated by Gemini before using it.
- Limited creativity: Gemini can sometimes generate ambiguous, repetitive, or unoriginal responses. This is especially true when asked to generate creative content, such as poems or code. This is because Gemini is still under development and is not always able to understand the nuances of human language.
Learning Resources
- Google blog: The Google blog regularly publishes articles and tutorials on how to use Gemini for different tasks. Click here to visit the Google blog.
Tips for using Gemini
- Be specific in your prompts. The more specific you are in your prompts; the better Gemini will be able to understand what you want.
- For example, instead of asking "What is the capital of France?", ask "What is the capital of France in 2023?".
- Use keywords. When you are asking Gemini to complete a task, try to include relevant keywords in your prompt. This will help Gemini to generate a more accurate and relevant response.
- For example, instead of asking "What is the best way to get to work?", ask "What is the best way to get to the Googleplex by public transportation?".
- Provide context. If you are asking Gemini to generate creative content, such as a poem or a story, try to provide as much context as possible. This will help Gemini to generate a more interesting and engaging response.
- For example, instead of asking "Write a poem about love", ask "Write a poem about a couple who falls in love while working on a science project together".
Use Cases
Security Considerations
- Do not enter confidential or sensitive information. Gemini is a public-facing tool, and any information you enter could be accessed by unauthorized third parties. Only provide Gemini with information that you are comfortable sharing with the public.
- Be aware of the potential for bias. Gemini is trained on a massive dataset of text and code, and it may reflect the biases present in that data. It is important to be critical of the information that Gemini generates and to verify it with other sources.
- Use Gemini responsibly. Avoid generating content that could harm others.
- Only use Gemini on trusted devices. Do not use Gemini on public computers or other devices that you do not control.
- Site your sources. Always disclose when you use Gemini and other generative AI resources in your work.
- Learn more about how Bard works and how Google uses your Gemini data.
Frequently Asked Questions
- Why can Gemini get things wrong?
-
Generative AI and all of its possibilities are exciting, but it is still new. Gemini is an experiment, and it can provide inaccurate information or make offensive statements.
Double-check the information you get from Gemini
Gemini has tools to help you identify potentially inaccurate statements. One way to double-check Gemini's responses is to use the Google button. This uses Google Search to find content that helps you assess and further research the information you get from Gemini.
Gemini's double-check feature can make mistakes
For example, the feature may show that Google Search found content that makes a similar statement to Gemini's. But the content may contradict Gemini. The web content may be inaccurate, too. You should read, review, and carefully evaluate the content identified by the double-check feature, as well as its context.
Help make Gemini better
Google relies on people to give feedback on answers that don’t seem right. That’s why Gemini has built-in features to collect your feedback, including marking good and bad responses and reporting legal issues.
Be mindful of how you use Gemini
You have an opportunity to shape Gemini for others. Gemini will use the conversations you have to improve future responses for everyone so don’t enter anything you wouldn’t want a reviewer to see or Google to use. -
How many languages does Gemini support?
-
Gemini is available in more than 40 languages, including: English, Japanese, Korean, Arabic, Bahasa Indonesia, Bengali, Bulgarian, Chinese (Simplified / Traditional), Croatian, Czech, Danish, Dutch, Estonian, Farsi, Finnish, French, German, Gujarati, Greek, Hebrew, Hindi, Hungarian, Italian, Kannada, Latvian, Lithuanian, Malayalam, Marathi, Norwegian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tamil, Telugu, Thai, Turkish, Ukrainian, Urdu and Vietnamese. We are continuing to teach Bard how to respond in even more languages.
-
Can Gemini connect with other Google apps and services?
-
Gemini can now respond with real-time information from Google Maps, Flights, Hotels, and YouTube, so you can get more done in one place. You can also choose to connect to Google Workspace, so Gemini can find, summarize, or answer questions about your content from Docs, Drive, and Gmail. Your Google Workspace content is kept private to you, which means it’s not used to improve Gemini.
If you’re using Gemini in English, you can turn off any of these extensions from the Extensions page.
Technical Support
https://support.gemini.com/hc/en-us
Content on this website is subject to change as AI tools continue to develop. Page last updated February 8, 2024.