On the Limits of Recursively Self-Improving AGI
نویسنده
چکیده
Self-improving software has been a goal of computer scientists since the founding of the field of Artificial Intelligence. In this work we analyze limits on computation which might restrict recursive self-improvement. We also introduce Convergence Theory which aims to predict general behavior of RSI systems.
منابع مشابه
Analysis of Types of Self-Improving Software
Software capable of improving itself has been a dream of computer scientists since the inception of the field. In this work we provide definitions for Recursively Self-Improving software, survey different types of self-improving software, and provide a review of the relevant literature. Finally, we address security implications from self-improving intelligent software.
متن کاملFrom Seed AI to Technological Singularity via Recursively Self-Improving Software
Software capable of improving itself has been a dream of computer scientists since the inception of the field. In this work we provide definitions for Recursively Self-Improving software, survey different types of self-improving software, review the relevant literature, analyze limits on computation restricting recursive self-improvement and introduce RSI Convergence Theory which aims to predic...
متن کاملAnalysis of Algorithms and Partial Algorithms
We present an alternative methodology for the analysis of algorithms, based on the concept of expected discounted reward. This methodology naturally handles algorithms that do not always terminate, so it can (theoretically) be used with partial algorithms for undecidable problems, such as those found in artificial general intelligence (AGI) and automated theorem proving. We mention an approach ...
متن کاملGOLEM: towards an AGI meta-architecture enabling both goal preservation and radical self-improvement
A high-level AGI architecture called GOLEM (Goal-Oriented LEarning Meta-Architecture) is presented, along with an informal but careful argument that GOLEM may be capable of preserving its initial goals while radically improving its general intelligence. As a metaarchitecture, GOLEM can be wrapped around a variety of different base-level AGI systems, and also has a role for a powerful narrow-AI ...
متن کاملTowards An Actual Gödel Machine Implementation: A Lesson in Self-Reflective Systems
Recently, interest has been revived in self-reflective systems in the context of Artificial General Intelligence (AGI). An AGI system should be intelligent enough to be able to reason about its own program code, and make modifications where it sees fit, improving on the initial code written by human programmers. A pertinent example is the Gödel Machine, which employs a proof searcher— in parall...
متن کامل