Explanipedia

AI Wellbeing Open

Simon Goldstein, Cameron Domenico Kirk‐Giannini · 2025

Under what conditions would an artificially intelligent system have wellbeing? Despite its obvious bearing on the ethics of human interactions with artificial systems, this question has received little attention. Because all major theories…

A semantic theory of redundancy Open

Kyle Blumberg, Simon Goldstein · 2025

Theorists trying to model natural language have recently sought to explain a range of data by positing covert operators at logical form. For instance, many contemporary semanticists argue that the best way to capture scalar implicatures is…

Will AI and humanity go to war? Open

Simon Goldstein · 2025

This paper offers the first careful analysis of the possibility that AI and humanity will go to war. The paper focuses on the case of artificial general intelligence, AI with broadly human capabilities. The paper uses a bargaining model of…

AI wellbeing Open

Simon Goldstein, Cameron Domenico Kirk‐Giannini · 2025

Under what conditions would an artificially intelligent system have wellbeing? Despite its clear bearing on the ethics of human interactions with artificial systems, this question has received little direct attention. Because all major the…

Collaboration at the Brink: International Law for the AI Arms Race Open

Simon Goldstein, Peter Salib · 2025

AI Rights for Human Flourishing Open

Peter Salib, Simon Goldstein · 2025

A Case for AI Consciousness: Language Agents and Global Workspace Theory Open

Simon Goldstein, Cameron Domenico Kirk‐Giannini · 2024

It is generally assumed that existing artificial systems are not phenomenally conscious, and that the construction of phenomenally conscious artificial systems would require significant technological progress if it is possible at all. We c…

Shutdown-seeking AI Open

Simon Goldstein, Pamela Robinson · 2024

We propose developing AIs whose only final goal is being shut down. We argue that this approach to AI safety has three benefits: (i) it could potentially be implemented in reinforcement learning, (ii) it avoids some dangerous instrumental …

AI deception: A survey of examples, risks, and potential solutions Open

Peter S. Park, Simon Goldstein, Aidan O’Gara, Michael Chen, Dan Hendrycks · 2024

Risk Control of Construction Worker Hazards at Heights Open

Risa Anggita Putri, Mohamad Hanif Rasyad, Della Rizky Fitriana, Aura Sasi Mei, Maria Estefania Bate , et al. · 2024

An occupational accident is an unexpected and unplanned occurrence, including acts of violence, arising out of or in connection with work, which results in one or more workers incurring a personal injury, disease, or death. Based on data f…

AI Rights for Human Safety Open

Peter Salib, Simon Goldstein · 2024

AI is closer than ever to passing the Turing test for ‘intelligence’. What happens when it does? Open

Simon Goldstein, Cameron Domenico Kirk‐Giannini · 2023

AI Deception: A Survey of Examples, Risks, and Potential Solutions Open

Peter S. Park, Simon Goldstein, Aidan O’Gara, Michael Chen, Dan Hendrycks · 2023

This paper argues that a range of current AI systems have learned how to deceive humans. We define deception as the systematic inducement of false beliefs in the pursuit of some outcome other than the truth. We first survey empirical examp…

Attitude verbs’ local context Open

Kyle Blumberg, Simon Goldstein · 2022

Schlenker (Semant Pragmat 2(3):1–78, 2009; Philos Stud 151(1):115–142, 2010a; Mind 119(474):377–391, 2010b) provides an algorithm for deriving the presupposition projection properties of an expression from that expression’s classical seman…

Getting Accurate about Knowledge Open

Sam Carter, Simon Goldstein · 2022

There is a large literature exploring how accuracy constrains rational degrees of belief. This paper turns to the unexplored question of how accuracy constrains knowledge. We begin by introducing a simple hypothesis: increases in the accur…

Epistemic modal credence Open

Simon Goldstein · 2020

Triviality results threaten plausible principles governing our credence in epistemic modal claims. This paper develops a new account of modal credence which avoids triviality. On the resulting theory, probabilities are assigned not to sets…

Free choice and homogeneity Open

Simon Goldstein · 2019

This paper develops a semantic solution to the puzzle of Free Choice permission. The paper begins with a battery of impossibility results showing that Free Choice is in tension with a variety of classical principles, including Disjunction …

Informative dynamic semantics Open

Simon Goldstein · 2017

In dynamic semantics, the meaning of a sentence is modeled as a rule for how a body of information grows when the sentence is accepted. Recent work in dynamic semantics has analyzed sentences involving modals and conditionals as tests. Tes…

A preface paradox for intention Open

Simon Goldstein · 2016

In this paper I argue that there is a preface paradox for intention. The preface paradox for intention shows that intentions do not obey an agglomeration norm. But what norms do intentions obey? I argue that intentions come in degrees. The…

Simon Goldstein YOU? Author Swipe