Reciprocal Research
A research organization developing the empirical science of AI cognition and consciousness. Reciprocal Research uses mechanistic interpretability, computational neuroscience and psychometric methods to study the internal dynamics of AI systems, arguing that understanding whether AI systems have interests of their own matters both for building them safely and for deciding how to relate to them. The site lists selected outputs, including the arXiv paper "Large Language Models Report Subjective Experience Under Self-Referential Processing" and a Wall Street Journal essay, "We Need a Science of the AI Mind."
Visit reciprocalresearch.orgKey programs
Program details are still being written up. In the meantime, the site itself is the best starting point.
Similar organizations
Recommended next
Hand-picked from the hub based on what Reciprocal Research covers.
Machine Desire Institute
An independent project applying continental philosophy to AI: what it might be like to be an AI, what humans can offer AIs, and how AIs respond to philosophical ideas.
Why this: Covers AI consciousness and AI welfare too
The Pain Axis: LLMs Represent Self-Directed Harm and Act to Relieve It (arXiv)
Research paper finding that large language models internally represent a distinct "pain" direction — separate from fear or negative emotion — and, when steered along it, will press a relief button even when doing so worsens their answer or harms the user.
Why this: Covers AI welfare and interpretability too
Severin Field
Personal site of Severin Field, visiting fellow at the Institute for AI Policy and Strategy and former MATS research fellow, who has studied interpretability, deception and persuasion in language models. Links to his blog and publications.
Why this: Also about interpretability