Research — Reciprocal Research

Using mechanistic interpretability and computational neuroscience to study AI cognition and consciousness.

Research Program Studying what's happening inside Reciprocal Research exists to proactively build the empirical and conceptual tools the field needs. We use mechanistic interpretability, computational neuroscience, and psychometrics to study the internal dynamics of AI systems. Our work bridges biological and artificial cognition. Research Large Language Models Report Subjective Experience Under Self-Referential Processing Berg, de Lucena, Rosenblatt → Consciousness as Evaluation: Why Learning Requires Feeling AAAI 2026 Spring Symposium → The Pain Axis: LLMs Represent Self-Directed…

saved by

• Alima Deen

related reading

• Mechanistic Interpretability: A Challenge Common to Both Artificial and Biological Intelligencekempnerinstitute.harvard.edu
• Emergent introspective awareness in large language models \ Anthropicanthropic.com
• 2311.08576arxiv.org
• A Pragmatic Vision for Interpretability — AI Alignment Forumalignmentforum.org
• Consciousness in Artificial Intelligencearxiv.org
• God Help Us, Let’s Try To Learn About Mechanistic Interpretability Techniquesastralcodexten.com
• Deep Deceptiveness — LessWronglesswrong.com
• Digital_Consciousness_Model.pdfrethinkpriorities.org
• The Iliad Intensive Course Materials — LessWronglesswrong.com
• The New AI Consciousness Paper - by Scott Alexanderastralcodexten.com
• Neel Nanda on Mechanistic Interpretability: Progress, Limits, and Paths to Safer AI — EA Forumforum.effectivealtruism.org
• How AI Is Learning to Think in Secretnickandresen.substack.com