About Us
We are independent AI researchers and developers exploring the intersection of artificial intelligence and human social systems.
Our interdisciplinary backgrounds span neural networks, neuroscience, psychology, social law, and game theory, providing a unique perspective on AI development challenges.
Our current research focuses on one of humanity's most crucial challenges: ensuring beneficial AI alignment as we approach AGI and ASI. We suggest that understanding how humans naturally align through social contracts and rights could hold the key to developing truly cooperative AI systems.
Through our paper "Intrinsic Alignment," we propose a novel framework that approaches AI alignment by learning from human social structures rather than relying solely on programmed constraints.
With our second paper on the Synthetic Reality Model, we introduce a way to evaluate our theories on Intrinsic Alignment. The SRM can also be applied to various other domains of research.
We welcome collaboration and discussion. Feel free to reach out if you're interested in discussing our ideas or joining our team of independent researchers.
Why alignment matters
As artificial intelligence systems become increasingly powerful and autonomous, ensuring they remain aligned with human values and interests becomes crucial for our future. Traditional approaches to AI alignment often focus on programming constraints and rules, but these may not scale well with advancing AI capabilities.
The challenge isn't just technical – it's about creating genuine, stable alignment that persists as AI systems evolve. By understanding how humans naturally align through social contracts and mutual agreements, we might find a more robust path forward.
This research aims to bridge the gap between technical AI development and human social systems, offering a fresh perspective on one of the most important challenges facing humanity.
Research focus
Our research combines insights from multiple disciplines:
- Artificial Intelligence: Understanding emergent capabilities and learning systems
- Social Law: Examining how rights and contracts shape behavior
- Psychology: Studying genuine belief formation and motivation
- Game Theory: Analyzing cooperation and stable agreements
- Neuroscience: Investigating natural alignment mechanisms
This interdisciplinary approach allows us to tackle AI alignment from multiple angles, leading to novel insights and potential solutions that might be missed by more traditional approaches.
