Скачать с ютуб Stephen Casper – Generalized Adversarial Training and Testing в хорошем качестве

Stephen Casper – Generalized Adversarial Training and Testing

Stephen Casper from MIT presenting 'Generalized Adversarial Training and Testing' on July 21, 2024 at the Vienna Alignment Workshop. Key Highlights: Addressing latent harmful capabilities in AI models Applying safety engineering principles to AI Ensuring AI robustness and safety through generalized adversarial training Mitigating risks with model manipulation and latent space attacks The Alignment Workshop is a series of events convening top ML researchers from industry and academia, along with experts in the government and nonprofit sectors, to discuss and debate topics related to AI alignment. The goal is to enable researchers and policymakers to better understand potential risks from advanced AI, and strategies for solving them. If you are interested in attending future workshops, please fill out the following expression of interest form to get notified about future events: http://far.ai/futures-eoi Find more talks on this YouTube channel, and at https://www.alignment-workshop.com/