Open Philanthropy recommended a grant of $30,000 to Sincxpress Education to support the development of an online course on mechanistic interpretability. Mechanistic interpretability is a field within AI safety focused on reverse-engineering the inner workings of neural networks to understand how they arrive at their decisions. The course will be distributed through the Udemy platform. In addition, this grant will support the creation of free educational content on YouTube.
This falls within our focus area of Global Catastrophic Risks Capacity Building.