AI & ML interests
This organization focuses on the systematic evaluation of artificial intelligence systems through the lens of consciousness research, integrating methods from machine learning, cognitive science, and computational neuroscience. Our objective is to develop technically grounded, falsifiable frameworks for assessing properties such as self-modeling, internal state integration, adaptive goal representation, and meta-learning, while remaining agnostic to strong claims of machine sentience. We emphasize operational definitions and reproducible benchmarks that probe whether advanced models exhibit measurable signatures analogous to constructs studied in human consciousness research, including global information integration, temporal coherence of internal representations, and higher-order inference. In parallel, we explore how perspectives from contemplative science and interdisciplinary consciousness studies can inform the design of evaluation protocols without introducing non-empirical assumptions. All work is conducted under strict scientific and ethical standards, avoiding anthropomorphic overinterpretation and ensuring that claims about AI systems remain evidence-based, transparent, and aligned with current consensus in the field.