Yoshua Bengio, the renowned figure in artificial intelligence (AI), has joined the Safeguarded AI project as its scientific director. This initiative aims to create an AI system that can understand and mitigate risks posed by other AI agents through the integration of scientific world models and mathematical proofs. The project, backed by the UK's Advanced Research and Invention Agency (ARIA), is set to receive a total investment of approximately £59 million ($69 million). Bengio emphasizes the need for robust mathematical guarantees to ensure AI systems function correctly before deployment, given the potential severe consequences of AI malfunctions or misuses. The project is divided into three technical areas: scaffolding, machine learning, and applications, each focusing on different aspects of developing a safer AI ecosystem. This move by Bengio highlights growing concerns within the academic community about AI risks, as exemplified by previous discussions involving other AI giants like Geoffrey Hinton, Andrew Ng, and Yann LeCun.