Welcome!

I’m Boden Moraski, a high school researcher and writer deeply passionate about AI Safety and the responsible development of artificial intelligence. I enjoy combining technical research with practical tool- and community-building to help ensure AI systems are developed safely and beneficially, while exploring how we can help people learn better and think more deeply about these crucial challenges.

Current Work

Right now I’m primarily interested in AI Safety, especially scalable oversight, risk and capabilities benchmarking, and prosaic alignment. I also believe that governance, advocacy, and community-building in AI Safety are all crucial to support and complement these research directions.

I’m also interested in ethical frameworks and how they interact and arise in both biological and artificial systems. I personally tend to operate through an ever-evolving amalgam of Virtue Ethics, Rationalism, Confucianism, and [Consequentialism]{https://plato.stanford.edu/entries/consequentialism/#ClasUtil}, predominantly in the context of Longtermism.

I’m currently engaged in several projects that align with these interests. As of writing this (July 2025), some of these include:

Leading development on the AI Ethical Compass, an educational platform using scenario-based learning to help teachers integrate responsible AI practices in their classrooms. The project was recognized as one of three featured initiatives worldwide in the Intel + ISTE AI Innovators Challenge.

Co-founding SPIG Technologies, an innovative group grading platform currently being piloted in U.S. schools. The platform aims to make collaborative assessment more efficient and accessible for educators. This was recently presented at the 2024 AP National Convention and U.S. Capitol.

Contributing to research at Carnegie Mellon University’s Philosophy and Computer Science departments, working on Sway - a dialogue platform that explores how AI can facilitate meaningful conversations while adhering to ethical principles. The platform has been adopted by over 30 colleges.

I’m also helping shape AI education through collaboration with AI4K12 on developing foundational curriculum for high school students, and serving as a technology research fellow at Frontlines Foundation, where I contribute to AI educational legislation.

Research Focus

My independent research explores moral alignment in large language models, specifically how chain-of-thought prompting affects ethical reasoning. I’m also developing quantum algorithms and optimization techniques, with work published and recognized at regional science fairs.

Recognition

Recent highlights include winning Pennsylvania’s Congressional App Challenge, placing 1st in state FBLA Data Analysis, and being selected as a HouseOfCode Lightning Talk speaker at the Capitol. I’m also a research fellow with Frontlines Foundation and was selected for the PAIR Program in the UK.

Get In Touch

I’m always interested in connecting with fellow researchers, builders, and anyone passionate about the intersection of AI, ethics, and education.