research
∙
02/16/2023
AI Risk Skepticism, A Comprehensive Survey
In this thorough study, we took a closer look at the skepticism that has...
share
research
∙
09/01/2021
Impossibility Results in AI: A Survey
An impossibility theorem demonstrates that a particular problem or set o...
research
∙
07/15/2021
Death in Genetic Algorithms
Death has long been overlooked in evolutionary algorithms. Recent resear...
research
∙
05/02/2021
AI Risk Skepticism
In this work, we survey skepticism regarding AI risk and show parallels ...
research
∙
04/22/2021
Understanding and Avoiding AI Failures: A Practical Guide
As AI technologies increase in capability and ubiquity, AI accidents are...
research
∙
08/07/2020
Uncontrollability of AI
Invention of artificial general intelligence is predicted to cause a shi...
research
∙
08/02/2020
Impossibility of Unambiguous Communication as a Source of Failure in AI Systems
Ambiguity is pervasive at multiple levels of linguistic analysis effecti...
research
∙
07/19/2020
On Controllability of AI
Invention of artificial general intelligence is predicted to cause a shi...
research
∙
07/11/2020
Human ≠ AGI
Terms Artificial General Intelligence (AGI) and Human-Level Artificial I...
research
∙
07/15/2019
Classification Schemas for Artificial Intelligence Failures
In this paper we examine historical failures of artificial intelligence ...
research
∙
06/20/2019
Unexplainability and Incomprehensibility of Artificial Intelligence
Explainability and comprehensibility of AI are important requirements fo...
research
∙
05/29/2019
Unpredictability of AI
The young field of AI Safety is still in the process of identifying its ...
research
∙
01/01/2019
Personal Universes: A Solution to the Multi-Agent Value Alignment Problem
AI Safety researchers attempting to align values of highly capable intel...
research
∙
11/14/2018
Emergence of Addictive Behaviors in Reinforcement Learning Agents
This paper presents a novel approach to the technical analysis of wirehe...
research
∙
10/27/2018
Uploading Brain into Computer: Whom to Upload First?
The final goal of the intelligence augmentation process is a complete me...
research
∙
10/12/2018
Why We Do Not Evolve Software? Analysis of Evolutionary Algorithms
In this paper, we review the state-of-the-art results in evolutionary co...
research
∙
10/02/2018
Human Indignity: From Legal AI Personhood to Selfish Memes
It is possible to rely on current corporate law to grant legal personhoo...
research
∙
09/30/2018
Optical Illusions Images Dataset
Human vision is capable of performing many tasks not optimized for in it...
research
∙
08/11/2018
Building Safer AGI by introducing Artificial Stupidity
Artificial Intelligence (AI) achieved super-human performance in a broad...
research
∙
05/23/2018
A Psychopathological Approach to Safety Engineering in AI and AGI
The complexity of dynamics in AI techniques is already approaching that ...
research
∙
12/11/2017
Detecting Qualia in Natural and Artificial Agents
The Hard Problem of consciousness has been dismissed as an illusion. By ...
research
∙
07/24/2017
Guidelines for Artificial Intelligence Containment
With almost daily improvements in capabilities of artificial intelligenc...
research
∙
07/09/2017
Evaluating race and sex diversity in the world's largest companies using deep neural networks
Diversity is one of the fundamental properties for the survival of speci...
research
∙
05/31/2017
The Singularity May Be Near
Toby Walsh in 'The Singularity May Never Be Near' gives six arguments to...
research
∙
10/25/2016
Artificial Intelligence Safety and Cybersecurity: a Timeline of AI Failures
In this work, we present and analyze reported failures of artificially i...
research
∙
09/01/2016
Verifier Theory and Unverifiability
Despite significant developments in Proof Theory, surprisingly little at...
research
∙
08/18/2016
On the Origin of Samples: Attribution of Output to a Particular Algorithm
With unprecedented advances in genetic engineering we are starting to se...
research
∙
06/22/2016
Artificial Fun: Mapping Minds to the Space of Fun
Yampolskiy and others have shown that the space of possible minds is vas...
research
∙
11/10/2015
Taxonomy of Pathways to Dangerous AI
In order to properly handle a dangerous Artificially Intelligent (AI) sy...
research
∙
02/23/2015
From Seed AI to Technological Singularity via Recursively Self-Improving Software
Software capable of improving itself has been a dream of computer scient...
research
∙
10/01/2014