A list of projects I am exploring for early 2025. These align with my technical interests in language models, interpretability, and AI alignment.
AI | LLM
Built as part of CS324 Large Language Models
AI | Interpretability
an interactive visualization of attention between tokens in a language model
VisitAI | Interpretability
a small tool that allows to easily access locally hosted LLMs internals from a jupyter notebook
Why include these upcoming projects?
These serve as my Lighthouse, helping focus my technical development in areas I'm passionate about. They represent the kind of complex challenges in AI systems that I'm eager to understand and contribute to as I continue growing in this field.
