Request for proposals for projects in AI alignment that work with deep learning systems

📖 Description

As part of our work on reducing [potential risks from advanced artificial intelligence](https://www.openphilanthropy.org/blog/potential-risks-advanced-artificial-intelligence-philanthropic-opportunity), Open Philanthropy is seeking proposals for projects working with deep learning systems that could help us understand and make progress on [AI alignment](https://www.openphilanthropy.org/focus/global-catastrophic-risks/potential-risks-advanced-artificial-intelligence/the-open-phil-ai-fellowship#examples): the problem of creating AI systems more capable than their designers that robustly try to do what their designers intended. We are interested in proposals that fit within certain research directions, described below and given as posts in the rest of [this sequence](https://www.alignmentforum.org/s/Tp3ryR4AxY56ctGh2), that we think could contribute to reducing the risks we are most concerned about.

📊 Game Impacts

💭 Reactions

🔗 Sources

• [1] https://www.alignmentforum.org/posts/H5iePjNKaaYQyZpgR/request-for-proposals-for-projects-in-ai-alignment-that-work