DeepMind researchers publish 'Assessing AI Consciousness' with Bayesian framework
mhutter42 · x · 2026-11-01
A new 270-page book, Assessing AI Consciousness: From Cacophony to Hierarchy, by Marcus Hutter and co-authors including Anil Seth, Murray Shanahan, and Shane Legg (DeepMind), is now available on Amazon. It introduces a Bayesian framework separating theoretical credence from empirical evidence, offering a precise, scalable method for calibrated AI consciousness assessments, with an accompanying online tool and open-source code. The motivation: as AI systems grow more capable and behaviorally compelling, expert disagreement about AI consciousness—and what consciousness even depends on—demands a shared framework.
Related event: DeepMind Researchers Publish Book on Assessing AI Consciousness(2 posts)→
More from AGI Musings
- Why honest AI pause advocates ask for 50 years: they want unpredictable new theory — panickssery · 2026-11-01
- Pause advocates pressed: how do you decide AI risk is low enough to resume? — panickssery · 2026-11-01
- Trust Infrastructure Will Matter More Than Benchmarks in the AI Era — AryHHAry · 2026-11-01
- Would a US AI slowdown push marginal researchers to China instead? — dfrsrchtwts · 2026-11-01
- 'You are a subagent': a take on task management in the AI era — lxfater · 2026-11-01
- Robin Hanson: Most people calling to 'pause' AI actually just want to limit it indefinitely — robinhanson · 2026-11-01