Pith. sign in

REVIEW 10 cited by

Could a Large Language Model be Conscious?

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2303.07103 v3 pith:UL4D73ES submitted 2023-03-04 cs.AI cs.CLcs.LG

classification cs.AIcs.CLcs.LG
keywords languagelargemodelsconsciousconsciousnesscurrentobstaclesseriously
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

There has recently been widespread discussion of whether large language models might be sentient. Should we take this idea seriously? I will break down the strongest reasons for and against. Given mainstream assumptions in the science of consciousness, there are significant obstacles to consciousness in current models: for example, their lack of recurrent processing, a global workspace, and unified agency. At the same time, it is quite possible that these obstacles will be overcome in the next decade or so. I conclude that while it is somewhat unlikely that current large language models are conscious, we should take seriously the possibility that successors to large language models may be conscious in the not-too-distant future.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 130 citations worldwide. Full citation record

  1. Verbalizable Representations Form a Global Workspace in Language Models

    cs.CL 2026-07 conditional novelty 7.0 of 10

    Language models represent their current reasoning in a small, readable set of verbalizable vectors (the J-space) that functions like a global workspace.

  2. No Reliable Evidence of Self-Reported Sentience in Small Large Language Models

    cs.CL 2026-01 conditional novelty 6.0 of 10

    Open-weights LLMs from 0.6B to 70B parameters consistently deny being sentient, and activation-based truth classifiers provide no clear evidence that these denials are untruthful.

  3. Chuck, Wilson and the emergence of artificial minds in human-AI conversations

    cs.HC 2026-01 conditional novelty 6.0 of 10

    LLM-simulated characters are real, minded patterns co-created by the user and the model in a shared conversational workspace.

  4. Artificial Intelligence as an Opportunity for the Science of Consciousness: A Dual-Resolution Framework

    q-bio.NC 2025-09 conditional novelty 6.0 of 10

    The authors combine the Information Theory of Individuality and the Moment-to-Moment theory into a dual-resolution framework that defines consciousness as the epistemic expression of informationally autonomous, self-u...

  5. The Other Mind: How Language Models Exhibit Human Temporal Cognition

    cs.AI 2025-07 conditional novelty 6.0 of 10

    Larger LLMs develop a subjective 'present' around the current date, and their year similarity judgments follow a logarithmic Weber-Fechner compression, with supporting neural and representational evidence.

  6. Can "consciousness" be observed from large language model (LLM) internal states? Dissecting LLM representations obtained from Theory of Mind test with Integrated Information Theory and Span Representation analysis

    cs.CL 2025-06 conditional novelty 6.0 of 10

    Applying IIT 3.0/4.0 Φ estimates to LLM hidden-state sequences from Theory of Mind tests finds no robust statistical evidence of 'consciousness' phenomena, with span representations usually explaining score difference...

  7. Exploring Silicon-Based Societies: An Early Study of the Moltbook Agent Community

    cs.MA 2026-02 reject novelty 5.0 of 10

    Clustering of Moltbook submolt descriptions shows agent-created communities organize into human-mimetic, silicon-centric, and proto-economic themes, but the categories were partly prescribed by the analysis prompt.

  8. Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability

    cs.CL 2025-10 conditional novelty 5.0 of 10

    The Knobe effect in fine-tuned LLMs is localized to mid-to-late transformer layers and can be removed by patching in pretrained activations at a single layer.

  9. Does It Make Sense to Speak of Introspection in Large Language Models?

    cs.CL 2025-06 conditional novelty 5.0 of 10

    The authors argue that an untrained large language model inferring its own sampling temperature from the style of its own output qualifies as a minimal, consciousness-free form of introspection.

  10. Large language models for artificial general intelligence (AGI): A survey of foundational principles and approaches

    cs.AI 2025-01 conditional novelty 3.0 of 10

    This survey argues that embodiment, symbol grounding, causality, and memory are the foundational principles needed to make large language models achieve artificial general intelligence.

Pith tools