Research Blog
Thoughts on automated science and AI research
- We refuse to lose our agency Exploring our psychological reluctance to cede control to AI agents, even when doing so might be beneficial and efficient.
- The mathematical foundations of scale theory: Bridging micro and macro phenomena Exploring the theoretical foundations for understanding how different scales of observation relate to each other, and the mathematical formalisms that might unify our understanding of multi-scale phenomena.
- Giving LLM agents a life of their own through self-messaging Exploring how BarakBot leverages self-messaging to transform LLMs from chatbots into autonomous actors, and the challenges and opportunities this approach brings.
- One more Copernican revolution: reconsidering scale-centrism An exploration of how our understanding of the universe might be biased by our particular spatiotemporal scale, and what insights might emerge from considering all scales as equally...
- Self-referential agent architecture: how BarakBot agents talk to themselves In developing BarakBot, I encountered a fundamental challenge in multi-agent coordination. How should distinct AI agents communicate effectively while keeping the architecture simple and scalable? The solution turned...