How can we ensure that AI systems are aligned with human values and ethical principles?

View Polygence scholar page
Project description
AI systems are becoming increasingly prominent and ubiquitous in our daily lives. For example, one can find AI systems in social media and in large language models (ex. ChatGPT) used to predict user behavior and text input. While these AI systems can be useful, they still have problems aligning with our human values. This paper will conduct a systematic review of ethical AI design methods, and discuss instances where these design methods assisted AI in aligning with human values. Then we will discuss how AI developing human consciousness may change the implementation of these design methods. This paper provides a potential way to think about how to manage AI in the case it develops human consciousness.

Project outcome
Wrote a research paper on how AI could potentially be managed if it developed consciousness.

Mentor review
She was very helpful during the writing and revising process.