AGI safety literature review

T Everitt, G Lea, M Hutter - arXiv preprint arXiv:1805.01109, 2018 - arxiv.org
The development of Artificial General Intelligence (AGI) promises to be a major event. Along
with its many potential benefits, it also raises serious safety concerns (Bostrom, 2014). The …

Towards safe artificial general intelligence

T Everitt - 2019 - search.proquest.com
The field of artificial intelligence has recently experienced a number of breakthroughs thanks
to progress in deep learning and reinforcement learning. Computer algorithms now …

A Stochastic Model of Mathematics and Science

DH Wolpert, DB Kinney - Foundations of Physics, 2024 - Springer
We introduce a framework that can be used to model both mathematics and human
reasoning about mathematics. This framework involves stochastic mathematical systems …

A theory of bounded inductive rationality

C Oesterheld, A Demski, V Conitzer - arXiv preprint arXiv:2307.05068, 2023 - arxiv.org
The dominant theories of rational choice assume logical omniscience. That is, they assume
that when facing a decision problem, an agent can perform all relevant computations and …

Hard Proofs and Good Reasons

S DeDeo - arXiv preprint arXiv:2410.18994, 2024 - arxiv.org
Practicing mathematicians often assume that mathematical claims, when they are true, have
good reasons to be true. Such a state of affairs is" unreasonable", in Wigner's sense …

[PDF][PDF] Verbal irony, pretense, and the common ground

R Cohn-Gordon, L Bergen - 2019 - reubencohngordon.com
We propose that verbal irony is a form of linguistic countersignaling, where agents engage
in pretense about the state of the world or the perspective they hold in order to communicate …

[PDF][PDF] Robot Consciousness

S Ripley - 2020 - osf.io
Interest has been renewed in the study of consciousness, both theoretical and applied,
following developments in 20th and early 21st century logic, metamathematics, computer …

A Meta-Doomsday Argument: Uncertainty About the Validity of the Probabilistic Prediction of the End of the World

A Turchin - 2018 - philpapers.org
Four main forms of Doomsday Argument (DA) exist—Gott's DA, Carter's DA, Grace's DA and
Universal DA. All four forms use different probabilistic logic to predict that the end of the …

Forecasting using incomplete models

V Kosoy - arXiv preprint arXiv:1705.04630, 2017 - arxiv.org
We consider the task of forecasting an infinite sequence of future observations based on
some number of past observations, where the probability measure generating the …

Robot Consciousness: Physics and Metaphysics Here and Abroad

SB Ripley - Journal of Big History, 2024 - veritas.journals.villanova.edu
Interest has been renewed in the study of consciousness, both theoretical and applied,
following developments in 20th and early 21st century logic, metamathematics, computer …