Research Index
Advancing the science
of intelligence.
We publish our findings to accelerate the safe development of AGI. Our work spans formal alignment, mechanistic interpretability, and planetary-scale systems.
Research Areas
Explore our specialized domains of inquiry.
From theoretical alignment to applied safety systems.
2 Areas Active
Area
Focus
Status
Activity
Breaking the Linearity Barrier: Recursive Swarms for Long-Horizon Engineering
active
How Dropstone Horizon Mode decouples reasoning depth from context length to enable 24+ hour autonomous engineering workflows.
active
Dec 19, 2025
The Dropstone D3 Neuro-Symbolic Architecture
active
Moving beyond "Monolithic Context" to a deterministic, state-managed runtime for high-assurance engineering agents.
active
Dec 19, 2025