The Machine Intelligence Research Institute is a nonprofit research organisation dedicated to ensuring the safety of advanced artificial intelligence.
The Machine Intelligence Research Institute (MIRI) studies the mathematical underpinnings of intelligent behaviour. It aims to further the development of artificial intelligence systems, ensuring the systems’ safety and reliability.
MIRI researchers don’t predict a specific timeline for the development of smarter-than-human artificially intelligent systems, but researchers generally agree that artificial intelligence will outperform humans in this century.
MIRI has developed a technical research agenda: Agent Foundations for Aligning Machine Intelligence with Human Interests. MIRI funds research that it thinks may be useful for making general-purpose artificial intelligence safe, reliable, well understood.
MIRI focuses on approaches to artificial intelligence that will remain transparent to humans (so that humans can understand why systems behave the way they do). It aims to develop an understanding of intelligent systems that behave as intended in novel settings.
We don't currently have further information about the cost-effectiveness of MIRI beyond it doing work in a high-impact cause area and taking a reasonably promising approach.
Funds / Organisations you select will show up here