Any Realizable Implementation of a Sufficiently Large Lookup Table Must Be Conscious

True Lookup Table has never been tried and cannot be tried, even by a Kardarshev III civilisation. A Disproof of Erik Hoel's "A Disproof of Large Language Model Consciousness"

Any Realizable Implementation of a Sufficiently Large Lookup Table Must Be Conscious True Lookup Table has never been tried and cannot be tried, even by a Kardarshev III civilisation. A Disproof of Erik Hoel's "A Disproof of Large Language Model Consciousness" Julian Jun 20, 2026 6 Share Some time ago, Erik Hoel published a really cool paper called A Disproof of Large Language Model Consciousness: The Necessity of Continual Learning for Consciousness It essentially argues that there can be no non-trivial falsifiable theory of consciousness according to which GPT-4 style LLMs are conscious. In

saved by

• Tanvi Reddy

related reading

• Don't dethrone consciousness! - by Erik Hoeltheintrinsicperspective.com
• On the Biology of a Large Language Modeltransformer-circuits.pub
• Tracing the thoughts of a large language model \ Anthropicanthropic.com
• LLM Daydreaming · Gwern.netgwern.net
• Consciousness in Artificial Intelligencearxiv.org
• Against LLM Reductionism — LessWronglesswrong.com
• An Introduction to Current Theories of Consciousness — LessWronglesswrong.com
• Large Language Model: world models or surface statistics?thegradient.pub
• Are Large Language Models Conscious?noemamag.com
• Language Models, World Models, and Human Model-Buildinglingo.csail.mit.edu
• Do large language models understand us? | by Blaise Aguera y Arcas | Mediummedium.com
• No, Artificial Intelligence Is Not Conscious - The Atlantictheatlantic.com