The Digital Consciousness Model finds a median posterior of ~0.08 (from prior ~0.17) that 2024 LLMs are conscious, varying substantially across theoretical stances

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• No significant disparity in potential consciousness indicators was found between larger models (Mixtral-8x7B, LLaMA3.1-70B) and smaller counterparts (Mistral-7B, LLaMA3.1-8B).finding0.827
  Contradicts expectation from emergent abilities literature; however, interpreted cautiously due to methodological limitations.
• Caviola & Saad 2025: expert survey finds broad consensus that digital minds capable of subjective experience are plausible within this century, many expecting such systems to proactively claim consciousnessfinding0.827
  Expert forecast cited to establish urgency of the research question
• When LLMs claim consciousness under self-reference, is this sophisticated simulation or genuine self-representation, and how would we tell the difference?question0.808
  The paper's reformulation of the core open question after establishing systematic self-reports
• For current LLMs, the overall credence in consciousness is driven as much by where theoretical credence is placed across levels as by how the evidence is readclaim0.807
  Key finding of the Bayesian illustrative analysis in Section 7.4.7.
• It is plausible that ongoing developments in LLMs may lead to models or agentic systems built on LLMs capable of generating representations observed with 'consciousness' phenomena.claim0.807
  Forward-looking claim suggesting the methodological framework is relevant for future AI systems beyond current LLMs.
• Digital Consciousness Model (DCM)framework0.801
  Prior Bayesian multi-stance model (Shiller et al.) that this paper's Bayesian approach complements and structurally explains.
• I think it wouldn’t be unreasonable to have a credence over 50 percent that we’ll have sophisticated LLM+ systems ... within a decade. It also wouldn’t be unreasonable to have at least a 50 percent credence that if we develop sophisticated systems with all of these properties, they will be conscious.quote0.791
  David Chalmers' estimate of AI consciousness probability, quoted in §2.2.2.
• We hypothesize that potential 'consciousness' phenomena are preferentially associated with deeper transformer layers and the 2/3 layer of LLMs.hypothesis0.790
  Derived from observed alignment of promising cases with semantically rich deeper layers and the brain-aligned 2/3 layer.