
Hi, I’m Cameron!
I am a UC Berkeley EECS student, passionate about developing safe, reliable and beneficial AI models.
Biography
I study Electrical Engineering and Computer Science at the University of California Berkeley, where I have had the opportunity to study under world-renowned faculty, and conduct research in several departments. I began my research journey working with Albert Qu, under PI Linda Wilbrecht in the Neuroscience department, where I first studied signal processing techniques for fiber photometric signals, and later the applications of recurrent mixture density networks on modeling experimental decision making under stochastic regimes. Most recently, I began working with Dr. Alane Suhr at BAIR (Berkeley Artificial Intelligence Research Lab), where I have been investigating task decomposition, context management and parallel reasoning in large language models.
I recognize the immense potential of artificial intelligence and machine learning in solving some of the greatest scientific questions of our time, however I also recognize that we need to dramatically advance our understanding of the internal mechanisms of these models, as well as vastly improve our safety and interpretability methodologies, in order to ensure that these increasingly powerful models are used in a provably beneficial capacity. To this end, I hope to pursue a PhD in Computer Science, with an emphasis on AI safety and interpretability.
Blog
No posts
Contacts
Location
Berkeley, CA