paper-with-me

Papers

Deconstructing Superintelligence: Identity, Self-Modification and Différance

2026-04-21 · Elija Perrier arxiv

Self-modification is routinely treated as constitutive of artificial superintelligence (\textbf{SI}), yet modification is a relative action requiring a \emph{supplement} outside the operation. We formalise this on an associative operator algebra $\mathcal{A}$ with update operator $\hat U$, difference operator $\hat D$, and self-representation operator $\hat R$, identifying the supplement with $\operatorname{Comm}(\hat U)$. 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 $[\hat T,Π_L]=0$, and \emph{class $\mathbf{A}$} 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 \emph{différance}. Our results show that the strong self-modification taken to define superintelligence may undermine the persistent identity upon which such systems are premised.

📄 PDF Abstract BibTeX arXiv:2604.19845

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Aligning Artificial Superintelligence via a Multi-Box Protocol

2025-11-26 · Avraham Yair Negozio arxiv

We propose a novel protocol for aligning artificial superintelligence (ASI) based on mutual verification among multiple isolated systems that self-modify to achieve alignment. The protocol operates by containing multiple…

Non-Evolutionary Superintelligences Do Nothing, Eventually

2016-09-07 · Telmo Menezes

There is overwhelming evidence that human intelligence is a product of Darwinian evolution. Investigating the consequences of self-modification, and more precisely, the consequences of utility function self-modification,…

Don't Fear the Reaper: Refuting Bostrom's Superintelligence Argument

2017-02-27 · Sebastian Benthall

In recent years prominent intellectuals have raised ethical concerns about the consequences of artificial intelligence. One concern is that an autonomous agent might modify itself to become "superintelligent" and, in sup…

On The Statistical Limits of Self-Improving Agents

2025-10-05 · Charles L. Wang, Keir Dorchen, Peter Jin arxiv

As systems trend toward superintelligence, a natural modeling premise is that agents can self-improve along every facet of their own design. We formalize this with a five-axis decomposition and a decision layer, separati…

Superintelligence cannot be contained: Lessons from Computability Theory

2016-07-04 · Manuel Alfonseca, Manuel Cebrian, Antonio Fernandez Anta, Lorenzo Coviello 외

Superintelligence is a hypothetical agent that possesses intelligence far surpassing that of the brightest and most gifted human minds. In light of recent advances in machine intelligence, a number of scientists, philoso…