Charlie O'Neill

I am a researcher and entrepreneur working at the intersection of LLMs, interpretability, and scientific applications. Currently, I'm preparing to begin my DPhil in Computer Science at Oxford as a General Sir John Monash Scholar. I've published on topics ranging from sparse autoencoders to category theoretical perspectives on self-attention.

Beyond academic research, I co-founded Rake News, which evolved from a peer-to-peer personalised news platform using LLMs into enterprise-grade RAG software solutions. I'm now working on Iris, a stealth project applying mechanistic interpretability to medical applications. Through my work at IMC Trading, Macuject (AI for ophthalmology), and CSIRO (climate forecasting), I've gained experience applying ML to diverse domains.

As a Tuckwell Scholar at ANU, I've had the privilege of working with Neel Nanda at Google DeepMind through the MATS program and David Klindt at Cold Spring Harbor Laboratory, exploring the intersection of neuroscience and ML interpretability. My primary interests lie in understanding the architectures of learning and meta-learning, and leveraging these insights to build better AI systems.