Machine Intelligence Research Institute

Yudkowsky

Nate Soares presenting an overview of the AI alignment problem at Google

Machine Intelligence Research Institute (MIRI), formerly known as the Singularity Institute for Artificial Intelligence (SIAI), is a non-profit organization focused on research related to artificial intelligence (AI) and its implications for humanity. MIRI's mission is to ensure that the creation of smarter-than-human intelligence has a positive impact. The institute is concerned with developing formal tools for the safe and beneficial management of advanced AI systems, with a particular focus on decision theory, mathematical logic, and machine learning.

History

MIRI was founded in 2000 by Eliezer Yudkowsky and others with the goal of addressing the potential risks and benefits associated with artificial general intelligence (AGI). Initially, the organization focused on promoting understanding and discussion of AGI and the technological singularity, a hypothetical future event when AI would surpass human intelligence. Over time, MIRI shifted its focus towards technical research aimed at ensuring future AI systems can be aligned with human values and controlled effectively.

Research Areas

MIRI's research agenda includes several key areas:

• Decision Theory: Investigating how AI systems can make decisions in a way that aligns with human values and ethics.
• Mathematical Logic: Developing formal systems that can help ensure AI behaviors remain predictable and safe as they evolve.
• Machine Learning: Exploring methods for AI systems to learn from data in a way that is transparent and controllable.
• AI Alignment: The study of techniques to ensure that AI systems' goals and behaviors are aligned with human intentions.

Impact and Criticism

MIRI has contributed to the broader discussion on AI safety and ethics, participating in academic conferences and publishing papers on the subject. The institute has also been involved in outreach and education efforts, aiming to raise awareness among policymakers, researchers, and the public about the potential risks and benefits of advanced AI.

However, MIRI's focus on long-term existential risks from superintelligent AI has been met with skepticism by some in the AI research community. Critics argue that immediate concerns, such as privacy, security, and economic displacement, deserve more attention. Supporters of MIRI's approach maintain that while short-term issues are important, it is also crucial to address potential long-term risks before they become unmanageable.

Funding

MIRI is supported by donations from individuals and organizations. It has received funding from various sources, including tech entrepreneurs and philanthropists interested in the future of AI and its societal impact.

See Also

• Artificial General Intelligence
• Technological Singularity
• AI Safety
• Future of Humanity Institute

This article is a medical stub. You can help WikiMD by expanding it!
Most recent articles Ongoing trials	Wikipedia