About Lachlan
Lachlan is a research student and Army Signals Officer who is passionate about Australia’s security and prosperity. His research focuses on AI safety, particularly mechanistic interpretability: the science of untangling how AI systems reason internally. Lachlan will undertake a PhD at Stanford University, where he aims to develop a new scientific paradigm both for understanding the inner workings of AI models and for shaping the ethical basis of their decision-making. He sees AI safety as a critical issue and believes Australia must be able to look inside and understand the systems it comes to rely on. He intends to return home with the tools necessary to audit foreign AI models’ brains and verify their trustworthiness. Working at the intersection of national security and academia, he will help ensure that AI in Australia is safe and fully aligned with Australia’s democratic values.
