fairfolio
Saved Projects

Quantifying Variability in AI Outputs

CSEF · 2026 Mathematical Sciences (Junior Division)

Mason Sung

Overview

Artificial intelligence (AI) has become quite common and can be found doing many different things. Around 73% of Americans show a willingness to incorporate AI into their daily lives (Pew Research Center). For people to use these AI effectively, it is important to know how an input prompt affects a response. It is proven AI has a broader range of outputs it can select from when an open-ended question is provided (Tempesta Media). In order to understand more about how a prompt and the following response are connected, multiple open-ended questions were created. These prompts were then entered into different AI models. I assume that each AI model will have its own unique response and will have a higher amount of variability. In order to make this variability more easy to understand I will transform the data by calculating things like the average word count. I will also include calculations that show the complexity of a response such as the Flesch reading ease and the Flesch-Kincaid grade level.

Competition history

  • CSEF 2026 Mathematical Sciences (Junior Division) · Entry J-14-11

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

Source: California Science & Engineering Fair public projects

Save projects to your library

Sign in with Google to keep track of projects you find interesting, organized into folders. An account also raises your daily allowance for “Has this been done?”, and lets you create a key for the MCP server with a much higher limit than anonymous use. Browsing stays public.

Continue with Google