Let Your Cre-AI-tivity Loose on the AI Playground
As the world of AI tools and applications continues to expand, you may be wondering, “How can I start exploring AI tools?”
University IT (UIT) is excited to share the new Stanford AI Playground pilot. This service gives Stanford faculty and staff an easy way to experiment with and compare some of the top AI technologies.
Based on feedback we receive from faculty and staff during this pilot phase, we will consider making the playground available to students later in the fall. Please note: The pilot duration could change or conclude based on the feedback we receive.
What is the AI Playground?
The AI Playground is a new platform built on open-source technology that provides access to various large language models (LLMs). The AI Playground is a place to learn and experiment. The AI Playground is not approved for high-risk data. Be sure to adhere to Stanford’s information security and privacy policies when using the Playground.
What can you do with the AI Playground?
The AI Playground is a Stanford-hosted, user-friendly platform to explore and experiment. The playground provides OpenAI’s ChatGPT, Google Gemini, Anthropic Claude, Meta’s Llama, DALL-E-3, Wolfram for computation and mathematics, Azure Assistants for data and coding analysis, and more.
Why use the AI Playground, and how does it work?
The AI Playground provides Stanford faculty and staff a unique environment to learn more about how leading AI technologies work. You can compare different commercially-available LLMs, without having to sign up for each one separately. In addition, you can move information between LLMs from different vendors. By hosting these tools on one platform, the AI Playground allows you to explore AI technologies in one place.
The AI Playground doesn’t offer every feature available directly from a vendor, and you may consider paying or subscribing to an AI tool in certain cases (for example, if you want AI integrated into another tool, such as Microsoft 365 Copilot).
However, new features are being added to the playground on a regular basis, and we encourage feedback from our Stanford community.
Quick start
To start, visit aiplayground.stanford.edu and log in with your Stanford credentials. On your first visit, you may see a one-time user settings screen to personalize your experience.
You can begin right away by typing a prompt (or using the microphone feature to speak your request) into the message field near the bottom center of your screen.
Choose activities
If you’re not quite sure where to start, here are a few types of tasks you might try:
- Summarize large amounts of information
- Discover insights and trends in information
- Make recommendations, such as professional development and career planning
- Improve existing documents and artifacts
- Skills assessment
Another fun approach: Try asking the LLM how to best structure a prompt around the question you are trying to answer and let the LLM tool guide you in your approach.
Then, to go deeper, you can explore the options at the top of the page, which allow you to adjust settings and switch among various LLMs. For a detailed guide of the many options in the AI Playground, visit the AI Playground Quick Start page.
What’s next, and what should I look out for?
The AI Playground is continually evolving, and we anticipate adding features regularly. Recently, UIT added LLM plugins for image generation, web scraping, and AI-assisted Google searches. Some upcoming features include additional AI Assistants for Stanford-specific content and improved analysis capabilities.
As the AI Playground is in its pilot phase, you might experience some quirky behavior or occasional outages during evening updates. Please remember the playground is not currently approved for high-risk data.
Additional information and providing feedback
- UIT’s GenAI Prompt Guide and GenAI Use Cases for Experimenting pages provide more specific guidance.
- To ask general questions and brainstorm with peers, join the Slack channel #ai-playground.
- For technical questions or support, send a Help request.
- Share your feedback with the project team by using the feedback form.
DISCLAIMER: UIT News is accurate on the publication date. We do not update information in past news items. We do make every effort to keep our service information pages up-to-date. Please search our service pages at uit.stanford.edu/search.
