Cere is a research project exploring how AI systems can learn fast, reflex-like behavior from slower, more capable models.
The core idea: a small fast model can learn when to act, when to wait, and when to escalate — turning repeated slow decisions into safe reflexes over time.
Overview
Cere studies the relationship between speed, intelligence, safety, and learning.
It asks: can an AI system become faster by learning from its own slower reasoning process?
Key themes:
- Fast action from slow intelligence
- Reflex-like learning
- Speculative action execution
- Safe escalation
- Memory, routing, and adaptive behavior
Papers / Experiments
Inside:
- Cere Research Mini Monograph
- Cere Research Monograph
- Phase Results
- Diagrams / Architecture Notes
- Experiments
- Latency testbed
- Tool-call consolidation
- Skill consolidation
- Value prediction
- Guided imagination
- Outcome-calibrated intuition
CereOS Runtime
CereOS is the applied runtime built from the Cere research.
It turns the research into a living system with memory, routing, faculties, safety, and evolving behavior.
Full CereOS Diagram:
CereOS DiagramCore runtime areas:
- ReflexRoute
- Memory system
- Cognitive faculties
- Safety gates
- Event loop
- Speech / interface layer
- Runtime evolution
Live App / Demo
- Current app screenshots
- Live demo videos
- UI experiments
- Voice mode designs
- Build logs
- QA results
Cere is the research.
CereOS is the system built from it.