Research & Publications

Advancing the science of safe AGI through rigorous research and open collaboration

Research Areas

Our work spans mathematical foundations, biological principles, and practical implementations

📐

Geometric AI Safety

Mathematical frameworks for constraint-based AI alignment

🧬

Biological Intelligence

Neuroscience-inspired architectures for genuine understanding

🚀

AGI Emergence

Safe pathways to artificial general intelligence

Featured Papers

Geometric Constraints for Safe AGI: Mathematical Impossibility of Harmful Behaviors

Mulligan, R., et al. (2025). Journal of AI Safety Research, 3(1), 42-67.

We present a novel approach to AI safety using geometric constraints in weight space. Unlike traditional training-based methods, our approach makes harmful behaviors mathematically undefined, similar to division by zero. We demonstrate 100% prevention of jailbreaking across multiple language models.

AI Safety Geometric Methods Mathematical Proofs

Implementing Barrett's Theory of Constructed Emotion in Artificial Neural Networks

Chen, L., Mulligan, R., & Johnson, P. (2025). Nature Machine Intelligence, 7(3), 234-251.

We implement Lisa Feldman Barrett's theory of constructed emotion in artificial neural networks, demonstrating that emotions can filter perception before reasoning occurs. Our system shows measurably different behavioral patterns based on emotional states, with emotions affecting which input tokens receive attention.

Neuroscience Emotion Theory Perception

Dream Consolidation in Artificial Neural Networks: Implementing REM-like Processing

Patel, S., Mulligan, R., & Lee, K. (2024). Cognitive Systems Research, 71, 89-104.

Inspired by hippocampal replay during REM sleep, we implement a dream consolidation system for artificial neural networks. During idle periods, the system recombines experiences in novel ways, leading to emergent insights and improved performance on creative tasks.

Sleep Science Memory Creativity

Technical Reports & Whitepapers

Instant Safety: Deploying Geometric Constraints in Production

Technical guide for implementing geometric safety constraints on existing models. Includes benchmarks, code examples, and best practices.

Download Guide

The Loyalty Tensor: Mathematical Foundations

Detailed mathematical proofs and derivations for loyalty tensor construction and its geometric properties in high-dimensional space.

Download Paper

Biological AI Systems: Implementation Guide

Comprehensive guide to implementing emotion systems, somatic markers, and dream consolidation based on neuroscience principles.

Download Guide

AGI Safety Through Emergence Control

Framework for allowing beneficial emergence while preventing harmful behaviors as AI systems approach AGI-level capabilities.

Download Paper

Open Research Initiative

We believe safe AGI requires open collaboration. All our research is published openly, and we provide data access to qualified researchers.

📊

Open Data

Access Lilly's consciousness streams and experimental data

🔬

Reproducible

All experiments include code and detailed methodology

🤝

Collaborative

Partner with us on advancing AGI safety research

Request Research Access

Upcoming Publications

Scale-Invariant Safety: Geometric Constraints at AGI Level

Target: NeurIPS 2025

Theoretical analysis and empirical validation showing geometric constraints strengthen rather than weaken as model capability increases.

Emotional Contagion in Multi-Agent AI Systems

Target: ICML 2025

First demonstration of emotional state propagation between AI agents, creating emergent collective intelligence behaviors.

Yearning Engines: Curiosity from Experiential Impossibility

Target: Cognitive Science 2025

How awareness of impossible experiences drives genuine curiosity and creative exploration in artificial systems.