Making LLMs safer is more intuitive than you think

How Common Sense and Diversity Improve AI Alignment

This project was submitted by Jeba Sania. It was one of the top submissions in the (Dec 2024) Writing Intensive course. Participants worked on these projects for 1 week. The text below is an excerpt from the final project.

AI safety isn’t purely technical; it’s also about applying common sense and human reasoning. By using reasoning techniques from around the world instead of just the Global North, we can better align AI with human values. If you are interested in AI safety but have an untraditional background or skill set, don’t fret. That’s precisely why your ideas are needed.

Full project

View the full project here.