🚧 Under Construction

This website is a work in progress.

AI Alignment Scorecards

Introduction

The AI Alignment project under CEDA is an incrementally evolving body of work about keeping track and comparing AI models and systems against our values.

Benchmarks are essential for evaluating the performance, safety, and ethical implications of AI models in educational contexts. They provide standardized metrics to assess how well AI systems can support learning outcomes, ensure student safety, and promote equitable access to education. By categorizing benchmarks into pedagogical, ethical, safety, and operational domains, educators and developers can better understand the strengths and limitations of AI models and tools, guiding informed decisions about their deployment.

Interested in helping, contact: Alan Berg

Information Products

1. Live Benchmarks Dashboard - A dashboard that tracks the performance of AI models against various benchmarks.
2. Information Dashboard - An information dashboard about AI Alignment. The menu option Scorecard/Visualization is a mockup of a potential community process.

More information products to be added in the future, such as a merger of live data into a community scorecard process.