# Deconstructing Superintelligence: Identity, Self-Modification and Diff'erance

arXiv: https://arxiv.org/abs/2604.19845 · HTML: https://mlsanity.com/paper/2604.19845/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 86 references that are in the map.
- First posted on arXiv 21 Apr 2026.

## Builds on (most cited first, 18 of 18)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](https://mlsanity.com/paper/2401.05566/) (2024)
- [Editing Large Language Models: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2305.13172/) (2023)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents](https://mlsanity.com/paper/2505.22954/) (2025)
- [Risks from Learned Optimization in Advanced Machine Learning Systems](https://mlsanity.com/paper/1906.01820/) (2019)
- [Evaluating the Ripple Effects of Knowledge Editing in Language Models](https://mlsanity.com/paper/2307.12976/) (2023)
- [Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram Perspective](https://mlsanity.com/paper/1908.04734/) (2019)
- [Is Power-Seeking AI an Existential Risk?](https://mlsanity.com/paper/2206.13353/) (2022)
- [Consciousness in Artificial Intelligence: Insights from the Science of Consciousness](https://mlsanity.com/paper/2308.08708/) (2023)
- [Scheming AIs: Will AIs fake alignment during training in order to get power?](https://mlsanity.com/paper/2311.08379/) (2023)
- [Taking AI Welfare Seriously](https://mlsanity.com/paper/2411.00986/) (2024)
- [Self-Modification of Policy and Utility Function in Rational Agents](https://mlsanity.com/paper/1605.03142/) (2016)
- [Computational Dualism and Objective Superintelligence](https://mlsanity.com/paper/2302.00843/) (2023)
- [Quantum AIXI: Universal Intelligence via Quantum Information](https://mlsanity.com/paper/2505.21170/) (2025)
- [Quantum AGI: Ontological Foundations](https://mlsanity.com/paper/2506.13134/) (2025)

## Built on by (most cited first, 1 of 1)

- [Post-AGI Economies: Superposition and the Second Fundamental Theorem of Welfare Economics](https://mlsanity.com/paper/2606.08267/) (2026)

## Abstract (arXiv)

Self-modification is routinely treated as constitutive of artificial superintelligence (SI), yet modification is a relative action requiring a supplement outside the operation. We formalise this on an associative operator algebra A with update operator hat U, difference operator hat D, and self-representation operator hat R, identifying the supplement with operatornameComm(hat U). A propagation theorem shows [hat U,hat R] decomposes through [hat U,hat D], so non-commutation propagates to self-representation. The liar paradox is the rank-one case [hat T,PiL]=0, and emphclass A systems, in which hat U acts on hat D, reproduce it at system scale, yielding a structure coinciding with Priest's inclosure schema and Derrida's diff'erance. Our results show that the strong self-modification taken to define superintelligence may undermine the persistent identity upon which such systems are premised.