{"schema":"postcutoff/event@1","as_of":"2026-11-19T22:11:00+01:00","url":"https://postcutoff.com/e/2026-09-28-deepmind-ai-consciousness-assessment-framework/","md":"https://postcutoff.com/e/2026-09-28-deepmind-ai-consciousness-assessment-framework/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-09-28-deepmind-ai-consciousness-assessment-framework","date":"2026-09-28","date_precision":"day","short_title":"Google DeepMind and collaborators propose a hierarchical Bayesian framework for assessing AI consciousness; LLM credences range from <0.01 to ~0.8","deck":null,"takeaway":"On Sept 28, 2026 a team led by Google DeepMind's Shamil Chandaria, with co-authors including Anil Seth, Murray Shanahan, Henry Shevlin, Chris Frith and DeepMind co-founder Shane Legg, posted \"From cacophony to hierarchy\" (arXiv 2609.35618).","category":"research","category_label":"Research","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"arXiv 2609.35618: From cacophony to hierarchy: a principled framework for assessing AI consciousness","url":"https://arxiv.org/abs/2609.35618","type":"paper","group":"primary","domain":"arxiv.org"},{"n":2,"title":"Shamil Chandaria on X: launch thread","url":"https://x.com/shamilch/status/2104901976165159018","type":"discussion","group":"reactions","domain":"x.com"},{"n":3,"title":"Iason Gabriel on X","url":"https://x.com/IasonGabriel/status/2104960037474984173","type":"discussion","group":"reactions","domain":"x.com"},{"n":4,"title":"samim: Should Google get to define what (AI) consciousness is? (critique)","url":"https://samim.io/p/2026-09-29-should-google-get-to-define-ai-consciousness","type":"discussion","group":"reactions","domain":"samim.io"},{"n":5,"title":"Zvi Mowshowitz: AI #188","url":"https://thezvi.substack.com/p/ai-188-gemini-dot-argon","type":"discussion","group":"reactions","domain":"thezvi.substack.com"}],"official":1,"filed":"2026-10-01","updated":"2026-10-01","orgs":["Google DeepMind"],"title":"Google DeepMind and collaborators propose a hierarchical Bayesian framework for assessing AI consciousness; LLM credences range from <0.01 to ~0.8","summary":"On Sept 28, 2026 a team led by Google DeepMind's Shamil Chandaria, with co-authors including Anil Seth, Murray Shanahan, Henry Shevlin, Chris Frith and DeepMind co-founder Shane Legg, posted \"From cacophony to hierarchy\" (arXiv 2609.35618). It places the major theories of consciousness on a five-level hierarchy of functional description and combines credences in the theories with indicator evidence in a Bayesian model. Applied to current LLMs, the result ranges from below 0.01 to about 0.8, depending on which theory one trusts.","key_facts":["arXiv 2609.35618, submitted Sept 28, 2026. Authors: Shamil Chandaria, Arvo Muñoz Morán, Fernando Rosas, Anil Seth, Henry Shevlin, Marcus Hutter, Thore Graepel, Adam Bales, Iulia Comsa, Murray Shanahan, Ruben Laukkonen, Morten Kringelbach, Chris Frith, Shane Legg","Separates the 'hard problem' from a tractable 'mapping problem': granting that experience supervenes on organisation, at which grain of description does the supervenience base sit?","Extends Marr's three levels into five: behavioural, computational, intrinsic causal-structural, organismic, organism-environment; substrate-dependent theories are treated as cross-cutting realisability constraints","Bayesian model: credences over theories × indicator evidence → overall credence; for current LLMs results span <0.01 to ~0.8, reflecting sensitivity to theoretical assumptions rather than a verdict","Released with an interactive assessment tool and a public code repository","Launch thread by Chandaria (~161k views); Iason Gabriel called it 'a tremendous paper'"],"key_numbers":[],"tags":["consciousness","model-welfare","philosophy","bayesian","ai-safety"],"science":null,"body_md":"## What happened\n\nRather than picking one theory of consciousness, the paper organizes the theories by the level of description each treats as decisive.\nIt then turns the disagreement into an explicit probability that can be updated with evidence about a given AI system.\n\n## Why it matters\n\nIt is the first major consciousness-assessment framework co-authored by a frontier lab's co-founder. It arrives as Anthropic's model\nwelfare work and religious leaders' debate over whether Claude is conscious draw public attention. Its wide credence range for LLMs\nshows how much depends on contested theory.","disputed":[],"related":[{"id":"2026-07-06-anthropic-global-workspace-j-lens","url":"https://postcutoff.com/e/2026-07-06-anthropic-global-workspace-j-lens/","date":"2026-07-06","date_precision":"day","short_title":"Anthropic finds a \"global workspace\" inside Claude using a Jacobian lens","deck":null,"takeaway":"It gives a way to read concepts a model is actively using but not saying, which could be used to detect hidden reasoning about deception or prompt injection.","category":"research","category_label":"Research","importance":4,"confidence":"medium","status":{"key":"partly","labels":["Partly confirmed"]},"sources":7,"official":3,"filed":"2026-09-29","updated":"2026-09-29","orgs":["Anthropic"]}],"people":[{"id":"shane-legg","name":"Shane Legg","url":"https://postcutoff.com/person/shane-legg/"},{"id":"zvi-mowshowitz","name":"Zvi Mowshowitz","url":"https://postcutoff.com/person/zvi-mowshowitz/"}],"posts":[{"id":"x-iasongabriel-2104960037474984173","title":"“A tremendous paper—and thread—about theories of consciousness, evidence, and what they…”","url":"https://postcutoff.com/p/x-iasongabriel-2104960037474984173/"},{"id":"x-shamilch-2104901976165159018","title":"“1/13 Can we assess AI consciousness without first solving consciousness itself? New from…”","url":"https://postcutoff.com/p/x-shamilch-2104901976165159018/"}],"videos":[],"models":[],"changes":[{"date":"2026-10-01","type":"filed","text":"Created (snowball from Zvi's AI #188)"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-01","run":null,"sources_read":null,"updated":"2026-10-01","human_review":null,"version":{"date":"2026-10-04"}},"gaps":[{"model_id":"gpt-6-2-astra","name":"GPT-6.2 Astra","cutoff":"2026-05","days_after":120,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":90,"in_training_data":false},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":181,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":120,"in_training_data":false}],"short_url":null}