Psychiatry
Cameron is MPhil student under Dr. Karen Ersche and is completing his thesis on Automating the Computational Modelling of Behaviour using LLMs. After graduation, he will pursue AI Safety research full-time over concerns of existential risks from advanced AI systems.
Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models: https://arxiv.org/abs/2412.01784
© 2025 University of Cambridge