Post-Cutoff

“1/13 Can we assess AI consciousness without first solving consciousness itself?”

Shamil Chandaria @shamilchX

Archived text

1/13 Can we assess AI consciousness without first solving consciousness itself?

New from Google DeepMind and collaborators across CS, neuroscience & philosophy:

“From cacophony to hierarchy: a principled framework for assessing AI consciousness”

https://arxiv.org/abs/2609.35618 🧵

Source: x.com/shamilch/status/2104901976165159018Archived 2026-10-01 via fxtwitter (unofficial).Counts: 161,519 views, 587 likes, 120 reposts, 61 replies (at fetch time)Media: image

Cited in

  1. Research 90 days after the cutoff

    Google DeepMind and collaborators propose a hierarchical Bayesian framework for assessing AI consciousness; LLM credences range from <0.01 to ~0.8