The potential for Large Language Models (LLMs) to attain technological singularity—the point at which artificial intelligence (AI) surpasses human intellect and autonomously improves itself—is a critical concern in AI research. This paper explores the feasibility of current LLMs achieving singularity by examining the philosophical and practical requirements for such a development. We begin with a historical overview of AI and intelligence amplification, tracing the evolution of LLMs from their origins to state-of-the-art models. We then proposes a theoretical framework to assess (...) whether existing LLM technologies could satisfy the conditions for singularity, with a focus on Recursive Self-Improvement (RSI) and autonomous code generation. We integrate key component technologies, such as Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO), into our analysis, illustrating how these could enable LLMs to independently enhance their reasoning and problem-solving capabilities. By mapping out a potential singularity model lifecycle and examining the dynamics of exponential growth models, we elucidate the conditions under which LLMs might self-replicate and rapidly escalate their intelligence. We conclude with a discussion of the ethical and safety implications of such developments, underscoring the need for responsible and controlled advancement in AI research to mitigate existential risks. Our work aims to contribute to the ongoing dialogue on the future of AI and the critical importance of proactive measures to ensure its beneficial development. (shrink)

Since the advent of computers, humans have pursued automata with superior information-processing capabilities. In the endeavor to create new entities that converge toward intellectual functions, the emergence of large language models (LLMs) that emulate AI surpassing ourselves has become a reality. With the intelligence explosion triggered by AI and the consequent emergence of superintelligence, the improvement of simulation capabilities accelerates. As this surpasses humans’ discriminative perceptual abilities between reality and unreality, a paradox arises wherein, from a modern scientific standpoint, science (...) becomes unscientific. It is thought that as our controllability over the reality we perceive is ultimately enhanced by superintelligence, even whether we ourselves exist, what happiness is, what ethics are, and whether concepts themselves ever existed become matters of uncertainty. -/- Note: In the creation of this paper, we have undertaken all writing ourselves and have not used generative AI for text generation except for translation purposes. (shrink)

In this study, we metaphysically discuss how societal values will change and what will happen to the world when superintelligence is safely realized. By providing a mathematical definition of superintelligence, we examine the phenomena derived from this thesis. If an intelligence explosion is triggered under safe management through advanced AI technologies such as large language models (LLMs), it is thought that a modern form of broken communism—where rights are bifurcated from the capitalist system—will first emerge. In that era, the value (...) of humans will ultimately eliminate external factors, and beings without superintelligence will converge into irreplaceable existences possessing only intrinsic value. The world will be divided into those who possess superintelligence and those who do not. For better or worse, global standardization will progress, and due to over-simulation accompanying the intelligence explosion, we may become unable to distinguish whether the reality we inhabit is original or a copy created through augmented reality. -/- Note: In the creation of this paper, we have undertaken all writing ourselves and have not used generative AI for text generation except for translation purposes. (shrink)

In this paper, first we discuss the conditions under which a Large Language Model (LLM) can emulate a superior LLM and potentially trigger an intelligence explosion, along with the characteristics and dangers of the resulting superintelligence. We also explore ``superalignment,'' the process of safely keeping an intelligence explosion under human control. We discuss the goals that should be set for the initial LLM that might trigger the intelligence explosion and the Self-Adversarial Surveillance (SAS) system, which involves having the LLM evaluate (...) its own output with different prompts to scalably respond to unexpected outputs that may arise with a certain probability. We aim to construct a theoretical framework for achieving safe superalignment based on specific experiments in the field of computer science using LLMs. However, since it also deals with the metaphysical aspect assuming superintelligence being achievable; that is, an intelligence explosion can occur, we present it as an interdisciplinary study between information science and philosophy. (shrink)

In this paper, we propose RSI-LLM (Recursively Self-Improving Large Language Model), which recursively executes its inference and improves its parameters to fulfill the instrumental goals of superintelligence: G1: Self-preservation, G2: Goal-content integrity, G3: Intelligence enhancement, and G4: Resource acquisition. We empirically observed the behavior of the LLM that tries to design tools to achieve G1~G4, within the autonomous self-improvement and knowledge acquisition. During interventions in these LLMs' coding experiments to ensure safetyness, we have also discovered that, as the creator of (...) the LLM, we are able to change or edit any of those LLMs' cognitive information about the world in any modality, including time, vision, hearing, etc. We discuss the relationship between us humans and these LLMs in the context of the creator and the creation of the observable universe. (shrink)

Self-emulation of automata is a switch to the ultimate state that leads the automaton into a never-ending loop. In this paper, we describe the technological singularity and critical points reached when a self-reproducing deterministic finite automaton, realized through modern AI technology, triggers an intelligence explosion, and we examine the phenomena that unfold beyond that point. We also explain the existence of a cognitive realm, one that surpasses humanity’s ability to distinguish reality from unreality caused by superintelligence, as well as the (...) new world created through its nesting. By understanding the properties of the perceptual matrix produced by deterministic finite automata, it becomes possible to offer a consistent explanation, one that does not contradict various theories, for why humanity cannot observe the randomly expanding colonies of extraterrestrial beings under a deterministic worldview in which “God does not play dice,” thereby providing a solution to the Fermi Paradox. We refer to this series of philosophical theories as “Emulationism,” and propose it here. Note: In the creation of this paper, we have undertaken all writing ourselves and have not used generative AI for text generation except for translation purposes. (shrink)