• Home
  • G Gordon Worley III
G Gordon Worley III

G Gordon Worley III
Phenomenological AI Safety Research Institute

Master of Science

About

9
Publications
293
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
21
Citations
Introduction
Gordon is our founder and Director of Research at the Phenomenological AI Safety Research Institute (PAISRI) where he is working to address existential risks created by artificial general intelligence. He was introduced to x-risks in the early 2000s by Nick Bostrom and Eliezer Yudkowsky, and after many years of looking for ways he could work to reduce them, he realized he could combine his interests in phenomenology, philosophy, mathematics, and AI to address x-risks through academic research. His current work focuses on using phenomenological methods to perform philosophical investigations into fundamental issues relevant to AGI alignment research.

Publications

Publications (9)
Preprint
Full-text available
The first group to build artificial general intelligence or AGI stands to gain a significant strategic and market advantage over competitors, so companies, universities, militaries, and other actors have strong incentives to race to build AGI first. An AGI race would be dangerous, though, because it would prioritize capabilities over safety and inc...
Preprint
Full-text available
The first group to build artificial general intelligence or AGI stands to gain a significant strategic and market advantage over competitors, so companies, universities, militaries, and other actors have strong incentives to race to build AGI first. An AGI race would be dangerous, though, because it would prioritize capabilities over safety and inc...
Preprint
Full-text available
The AGI alignment problem has a bimodal distribution of outcomes with most outcomes clustering around the poles of total success and existential, catastrophic failure. Consequently, attempts to solve AGI alignment should, all else equal, prefer false negatives (ignoring research programs that would have been successful) to false positives (pursuing...
Article
Computational techniques to analyze and verify computer programs give developers powerful tools to write correct programs that accomplish their intended goals. In this paper, we explain the mathematical foundations of program analysis and verification and look at the program analysis and verification tools available on Mac OS X.
Article
Given a graph G, the security number of G is the cardinality of a minimum secure set of G, the smallest set of vertices S ⊆ V (G) such that for all X ⊆ S, |N [X] ∩ S| ≥ |N [X] − S|. It is believed to be computationally difficult to find the security number of large graphs, so we present techniques for reducing the difficulty of both finding a secur...
Article
Full-text available
We consider storing the pages of a wiki in a tuple space and the effects this might have on the wiki experience. In particular, wiki pages are stored in tuples with a few identifying values such as title, author, revision date, content, etc. and pages are retrieved by sending the tuple space templates, such as one that gives the title but nothing e...
Article
Full-text available
In 2003, Bechmann-Pasquinucci introduced the concept of quantum seals, a quantum analogue to wax seals used to close letters and envelopes. Since then, some improvements on the method have been found. We first review the current quantum sealing techniques, then introduce and discuss potential applications of quantum message sealing, and conclude wi...
Article
Full-text available
Central to the power of open-source software is bug shallowness, the relative ease of finding and fixing bugs. The open-source movement began with Unix software, so many users were also programmers capable of finding and fixing bugs given the source code. But as the open-source movement reaches the Macintosh platform, bugs may not be shallow becaus...
Article
Full-text available
We present a so-called fuzzy watermarking scheme based on the relative frequency of error in observing qubits in a dissimilar basis from the one in which they were written. Then we discuss possible attacks on the system and speculate on how to implement this watermarking scheme for particular kinds of messages (images, formated text, etc.).

Network

Cited By

Projects

Projects (2)