DeepMind and Researchers Unveil Bayesian Framework for Assessing AI Consciousness

Google DeepMind and 14 scholars including Anil Seth and Shane Legg published an arXiv paper proposing a pragmatic Bayesian framework for evaluating AI consciousness. Their tool rates mainstream LLMs between 1% and 80%, offering a new quantitative approach to the field.

2026-09-29 ~ 2026-09-29 · 3 related posts

• Bayesian framework from DeepMind-linked researchers scores LLM consciousness between 1% and 80% — mhutter42 · 2026-09-29
• DeepMind and Anil Seth publish principled framework for assessing AI consciousness — anilkseth · 2026-09-29
• Shane Legg and leading consciousness researchers release tool scoring LLMs 1%-80% on consciousness credence — mhutter42 · 2026-09-29