# Let's Keep It Safe: Designing User Interfaces that Allow Everyone to Contribute to AI Safety

## TL;DR

This paper explores the design of user interfaces that enable diverse users to contribute effectively to specifying safety constraints for AI systems, improving safety and efficiency in real-world applications.

## Contribution

It introduces a novel rule-based user interface for constraint specification that is expressive, scalable, and enhances data quality through improved filtering and explanations.

## Key findings

- Rule-based interface retains full expressiveness
- Filtering and explanation methods outperform baselines
- Workers are more efficient and produce higher quality data

## Abstract

When AI systems are granted the agency to take impactful actions in the real world, there is an inherent risk that these systems behave in ways that are harmful. Typically, humans specify constraints on the AI system to prevent harmful behavior; however, very little work has studied how best to facilitate this difficult constraint specification process. In this paper, we study how to design user interfaces that make this process more effective and accessible, allowing people with a diversity of backgrounds and levels of expertise to contribute to this task. We first present a task design in which workers evaluate the safety of individual state-action pairs, and propose several variants of this task with improved task design and filtering mechanisms. Although this first design is easy to understand, it scales poorly to large state spaces. Therefore, we develop a new user interface that allows workers to write constraint rules without any programming. Despite its simplicity, we show that our rule construction interface retains full expressiveness. We present experiments utilizing crowdworkers to help address an important real-world AI safety problem in the domain of education. Our results indicate that our novel worker filtering and explanation methods outperform baseline approaches, and our rule-based interface allows workers to be much more efficient while improving data quality.