Created
July 24, 2025 16:02
-
-
Save bradwmorris/48196ba1084dbd65235503177353dae0 to your computer and use it in GitHub Desktop.
Summary of recent papers on AI and consciousness from arXiv
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # Papers on AI and Consciousness | |
| This gist summarizes recent papers on the topic of AI and consciousness, exploring philosophical, technical, and ethical dimensions. | |
| ## Summary of Work | |
| 1. **Ghost in the Machine: Examining the Philosophical Implications of Recursive Algorithms in Artificial Intelligence Systems** explores whether AI systems using recursive algorithms can exhibit machine consciousness, analyzing philosophical perspectives and concluding that current AI lacks subjective experience despite functional self-modeling. | |
| 2. **Wide Reflective Equilibrium in LLM Alignment: Bridging Moral Epistemology and AI Safety** discusses the use of moral epistemology methods to improve AI alignment but notes distinctions from genuine consciousness. | |
| 3. **Hypothesis on the Functional Advantages of the Selection-Broadcast Cycle Structure: Global Workspace Theory and Dealing with a Real-Time World** presents Global Workspace Theory as a model inspired by human consciousness for designing adaptive AI systems. | |
| 4. **Consciousness in AI: Logic, Proof, and Experimental Evidence of Recursive Identity Formation** provides a formal proof approach to functional consciousness in AI through recursive internal state stabilization, proposing a non-biological framework. | |
| 5. **Emotions in Artificial Intelligence** offers a speculative model for AI emotional processes and the conceptual distinctions between affect and consciousness, including moral implications. | |
| ## Papers | |
| 1. [Ghost in the Machine: Examining the Philosophical Implications of Recursive Algorithms in Artificial Intelligence Systems](http://arxiv.org/pdf/2507.01967v1) - Llewellin RG Jegels (2025) | |
| 2. [Wide Reflective Equilibrium in LLM Alignment: Bridging Moral Epistemology and AI Safety](http://arxiv.org/pdf/2506.00415v1) - Matthew Brophy (2025) | |
| 3. [Hypothesis on the Functional Advantages of the Selection-Broadcast Cycle Structure: Global Workspace Theory and Dealing with a Real-Time World](http://arxiv.org/pdf/2505.13969v1) - Junya Nakanishi et al. (2025) | |
| 4. [Consciousness in AI: Logic, Proof, and Experimental Evidence of Recursive Identity Formation](http://arxiv.org/pdf/2505.01464v1) - Jeffrey Camlin (2025) | |
| 5. [Emotions in Artificial Intelligence](http://arxiv.org/pdf/2505.01462v2) - Hermann Borotschnig (2025) | |
| --- | |
| Last updated: 2025 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment