Full Bio - CV - Publications

I’m a Member of Technical Staff at FAR.AI and a PhD candidate at McGill University and the Mila AI Institute.

I lead cross-functional teams building solutions on technical foundations. Our work aims to uncover, understand, and solve AI risks across misuse, misalignment, and loss of control. Some active lines of work span persuasion, tampering, red-teaming, evaluation, and demos. My past work has exposed vulnerabilities and risks of models from every frontier AI company, influencing industry and governments. It has also been published in top venues such as NeurIPS, ICML, AAAI, EMNLP, KDD, and WebConf, and has been featured multiple times by press like the Financial Times, The Times, Vice, Scientific American, and Nature Magazine. For beating superhuman AIs that play the board game Go I’ve been called the “man who beat the machine”.