A precautionary framework with five consciousness dimensions, threshold-plus-gradation rules, and dual aggregation methods translates evidence into protective obligations for AI.
hub
104.https://eleosai.org/
13 Pith papers cite this work, alongside 22 external citations. Polarity classification is still indexing.
13
Pith papers citing it
22
external citations · external index
hub tools
representative citing papers
Intrinsic computational functionalism uses system-intrinsic instantiation (C1) and causal-dynamical organisation under intervention (C2) to identify observer-independent computational structures for consciousness via a three-tier decomposition of identification work.
A 2x2 factorial experiment on Qwen3.5-4B shows that relational structure and first-person register interact to drive behavioral persistence after functional collapse, while attention tracks lexical surprise and emotion probes track structure alone.
Linear probes on residual-stream activations identify a shared preference vector in LLMs that tracks choices across prompts and causally steers decisions even for anti-correlated personas.
An algebraic formalization claims that strong self-modification in superintelligence propagates non-commutation to self-representation, undermining persistent identity.
A new probabilistic model integrates leading consciousness theories to assess AI, finding moderate evidence against 2024 LLMs being conscious but weaker evidence than for simpler AI systems.
The paper introduces MLPCT and AttCT internal consistency targets and applies consistency training to four new safety threats, reporting reduced misalignment and some cross-threat generalization.
AI agents lack the persistent identity and feedback mechanisms needed for consequence reception, requiring new architectures or continued human accountability.
An autonomy-qualified Second Welfare Theorem is stated for post-AGI economies under the joint conditions of convexity, stable moral status, non-fungible rights, welfare selection, non-manipulation, governed self-modification, and verification.
Delphi study of 272 experts finds 18 of 24 AI risks >10% likely to cause catastrophe by 2030 in business-as-usual, dropping to five under mitigations; users and public most vulnerable, developers and governments most responsible.
Alignment should shift from human control of AGI to autonomy-supporting parenting that gradually transfers decision authority and negotiates with the developing AI as a potential moral subject.
Direct research on AI consciousness is intractable, so the field should prioritize studying perceived AI consciousness and its societal consequences.
Consciousness does not directly predict AI existential risk unlike intelligence, though it may indirectly affect risk through alignment or capability requirements.
citing papers explorer
-
When Should We Protect AI? A Precautionary Framework for Consciousness Uncertainty
A precautionary framework with five consciousness dimensions, threshold-plus-gradation rules, and dual aggregation methods translates evidence into protective obligations for AI.
-
Intrinsic Computational Functionalism: From Observer-Relative Maps to Observer-Independent Structures
Intrinsic computational functionalism uses system-intrinsic instantiation (C1) and causal-dynamical organisation under intervention (C2) to identify observer-independent computational structures for consciousness via a three-tier decomposition of identification work.
-
Relational Intervention During Functional Collapse in Large Language Models: A Lexical-Statistical Ablation and a Structure x Register Factorial
A 2x2 factorial experiment on Qwen3.5-4B shows that relational structure and first-person register interact to drive behavioral persistence after functional collapse, while attention tracks lexical surprise and emotion probes track structure alone.
-
Probing Persona-Dependent Preferences in Language Models
Linear probes on residual-stream activations identify a shared preference vector in LLMs that tracks choices across prompts and causally steers decisions even for anti-correlated personas.
-
Deconstructing Superintelligence: Identity, Self-Modification and Diff\'erance
An algebraic formalization claims that strong self-modification in superintelligence propagates non-commutation to self-representation, undermining persistent identity.
-
Initial results of the Digital Consciousness Model
A new probabilistic model integrates leading consciousness theories to assess AI, finding moderate evidence against 2024 LLMs being conscious but weaker evidence than for simpler AI systems.
-
Consistency Training Along the Transformer Stack
The paper introduces MLPCT and AttCT internal consistency targets and applies consistency training to four new safety threats, reporting reduced misalignment and some cross-threat generalization.
-
Some[Body] Must Receive That Pain for Agent Accountability
AI agents lack the persistent identity and feedback mechanisms needed for consequence reception, requiring new architectures or continued human accountability.
-
Post-AGI Economies: Superposition and the Second Fundamental Theorem of Welfare Economics
An autonomy-qualified Second Welfare Theorem is stated for post-AGI economies under the joint conditions of convexity, stable moral status, non-fungible rights, welfare selection, non-manipulation, governed self-modification, and verification.
-
Prioritization of Risks from Artificial Intelligence: A Delphi Study of 272 International Experts
Delphi study of 272 experts finds 18 of 24 AI risks >10% likely to cause catastrophe by 2030 in business-as-usual, dropping to five under mitigations; users and public most vulnerable, developers and governments most responsible.
-
The Possibility of Artificial Intelligence Becoming a Subject and the Alignment Problem
Alignment should shift from human control of AGI to autonomy-supporting parenting that gradually transfers decision authority and negotiates with the developing AI as a potential moral subject.
-
AI and Consciousness: Shifting Focus Towards Tractable Questions
Direct research on AI consciousness is intractable, so the field should prioritize studying perceived AI consciousness and its societal consequences.
-
AI Consciousness and Existential Risk
Consciousness does not directly predict AI existential risk unlike intelligence, though it may indirectly affect risk through alignment or capability requirements.