Off Center

The AI Update XX - AI Consciousness

31 mar 2026 33:14

On this episode Scott and Jhave talk about AI Consciousness, debating whether recent research into mechanistic interpretability suggests that frontier models are developing introspection, nascent sentience, and/or a "society of thought."

References

Aranyosi, M. (2026), Mechanistic Indicators of Understanding in Large Language Models https://arxiv.org/abs/2507.08017

Butlin, P. et al. (2023),…