Fetching the paper…
Reading the bibliography…
As AI technologies increase in capability and ubiquity, AI accidents are becoming more common.
Ironies of automation
Lisanne Bainbridge · 1983
Earlier work this paper cites.
The calculus of cooperation is tested through a lottery
Douglas R. Hofstadter · 1983
Earlier work this paper cites.
Normal Accidents: Living with High Risk Technologies
Charles Perrow · 1984
Earlier work this paper cites.
A strawman speaks up: Comments on the limits of safety
Todd R. La Porte · 1994
Earlier work this paper cites.
Social dilemma behavior of individuals from highly individualist and collectivist cultures
Craig D. Parks and Anh D. Vu · 1994
Earlier work this paper cites.
Risk management in a dynamic society: a modelling problem
Jens Rasmussen · 1997
Earlier work this paper cites.
How complex systems fail
Richard I. Cook · 1998
Earlier work this paper cites.
The split brain revisited
Michael S. Gazzaniga · 1998
Earlier work this paper cites.
Complexity, Coupling, and Catastrophe
Charles Perrow · 1999
Earlier work this paper cites.
Organizing for high reliability: Processes of collective mindfulness
K. Weick, K. Sutcliffe, and David Obstfeld · 1999
Earlier work this paper cites.
Friendly Fire
S.A. Snook · 2000
Earlier work this paper cites.
Existential risks - analyzing human extinction scenarios and related hazards
Nick Bostrom · 2001
Earlier work this paper cites.
Failures of adaptive control theory and their resolution
Brian D. O. Anderson · 2005
Earlier work this paper cites.
Standardizing measurements of autonomy in the artificially intelligent
Amy Hudson and Larry Reeker · 2007
Earlier work this paper cites.
A survey on virtual machine security
J. Reuben · 2007
Earlier work this paper cites.
On Slippery Slopes, Repeating Negative Patterns, and Learning from Mistake?
Diane Vaughan · 2007
Earlier work this paper cites.
Hard takeoff
Eliezer Yudkowsky · 2008
Earlier work this paper cites.
Normal accident theory versus high reliability theory: A resolution and call for an open systems view of accidents
Samir Shrivastava, Karan Sonpar, and Federica Pazzaglia · 2009
Earlier work this paper cites.
The Most Human Human: What Talking with Computers Teaches Us About What It Means to Be Alive
B. Christian · 2011
Earlier work this paper cites.
Complex value systems in friendly AI
Eliezer Yudkowsky · 2011
Earlier work this paper cites.
The Righteous Mind: Why Good People Are Divided by Politics and Religion
J. Haidt · 2012
Earlier work this paper cites.
Leakproofing the singularity artificial intelligence confinement problem
Roman V Yampolskiy · 2012
Cited alongside, same era.
Superintelligence: Paths, Dangers, Strategies
Nick Bostrom · 2014
Cited alongside, same era.
The ethics of artificial intelligence
Nick Bostrom and Eliezer Yudkowsky · 2014
Cited alongside, same era.
Safe exploration of state and action spaces in reinforcement learning
Javier García and Fernando Fernández · 2014
Cited alongside, same era.
South Korean woman’s hair ‘eaten’ by robot vacuum cleaner as she slept
Justin McCurry · 2015
Cited alongside, same era.
How the technology of iRobot Roomba self cleaning robot vacuum works
Maya Wilkinson · 2015
Cited alongside, same era.
Global AI ethics: A review of the social impacts and ethical implications of artificial intelligence, 2019
Alexa Hagerty and Igor Rubinov · 2019
Later among the works it cites.
Adversarial examples are not bugs, they are features
Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Logan Engstrom, Brandon Tran, and Aleksander Madry · 2019
Later among the works it cites.
AI safety needs social scientists
Geoffrey Irving and Amanda Askell · 2019
Later among the works it cites.
Towards deep learning models resistant to adversarial attacks, 2019
Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu · 2019
Later among the works it cites.
One pixel attack for fooling deep neural networks
J. Su, D. V. Vargas, and K. Sakurai · 2019
Later among the works it cites.
Grandmaster level in StarCraft II using multi-agent reinforcement learning
Oriol Vinyals, Igor Babuschkin, Wojciech M Czarnecki, Michaël Mathieu, Andrew Dudzik, Junyoung Chung, David H Choi, Richard Powell, Timo Ewalds, Petko Georgiev, Junhyuk Oh, Dan Horgan, Manuel Kroiss, Ivo Danihelka, Aja Huang, Laurent Sifre, Trevor Cai, John P Agapiou, Max Jaderberg, Alexander S Vezhnevets, Rémi Leblond, Tobias Pohlen, Valentin Dalibard, David Budden, Yury Sulsky, James Molloy, Tom L Paine, Caglar Gulcehre, Ziyu Wang, Tobias Pfaff, Yuhuai Wu, Roman Ring, Dani Yogatama, Dario Wünsch, Katrina McKinney, Oliver Smith, Tom Schaul, Timothy Lillicrap, Koray Kavukcuoglu, Demis Hassabis, Chris Apps, and David Silver · 2019
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Concrete problems in AI Safety
Dario Amodei, Chris Olah, J. Steinhardt, Paul F. Christiano, John Schulman, and Dan Mané · 2016
Cited alongside, same era.
The agi containment problem
James Babcock, Janos Kramar, and Roman Yampolskiy · 2016
Cited alongside, same era.
Microsoft chat bot goes on racist, genocidal Twitter rampage
Damon Beres · 2016
Cited alongside, same era.
Cooperative inverse reinforcement learning
Dylan Hadfield-Menell, Stuart J Russell, Pieter Abbeel, and Anca Dragan · 2016
Cited alongside, same era.
Normal autonomous accidents: What happens when killer robots fail?
Stephanie Carvin · 2017
Cited alongside, same era.
The flash crash: High-frequency trading in an electronic market
Andrei Kirilenko, Albert S. Kyle, Mehrdad SAMADI, and Tugkan Tuzun · 2017
Cited alongside, same era.
Later among the works it cites.
Predicting future AI failures from historic examples
Roman V. Yampolskiy · 2019
Later among the works it cites.
Language models are few-shot learners, 2020
Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei · 2020
Later among the works it cites.
Explainable AI for system failures: Generating explanations that improve human assistance in fault recovery, 2020
Devleena Das, Siddhartha Banerjee, and Sonia Chernova · 2020
Later among the works it cites.
Inverse reward design, 2020
Dylan Hadfield-Menell, Smitha Milli, Pieter Abbeel, Stuart Russell, and Anca Dragan · 2020
Later among the works it cites.
An AI tool which reconstructed a pixelated picture of Barack Obama to look like a white man perfectly illustrates racial bias in algorithms
Isobel Asher Hamilton · 2020
Later among the works it cites.
The surprising creativity of digital evolution: A collection of anecdotes from the evolutionary computation and artificial life research communities
Joel Lehman et al · 2020
Later among the works it cites.
The AI accident network: Artificial intelligence liability meets network theory
Anat Lior · 2020
Later among the works it cites.
Anthropomorphism in AI
Arleen Salles, Kathinka Evers, and Michele Farisco · 2020
Later among the works it cites.
Classification schemas for artificial intelligence failures
Peter J. Scott and Roman V. Yampolskiy · 2020
Later among the works it cites.
Alignment for advanced machine learning systems, 2020
Jessica Taylor, Eliezer Yudkowsky, Patrick LaVictoire, and Andrew Critch · 2020
Later among the works it cites.
HAL 9000
Anonymous · 2021
Closest in time.
C. Badea and Gregory Artus · 2021
Closest in time.
What are technology readiness levels (trl)?
TWI Ltd · 2021
Closest in time.
AI incident database
Sean McGregor, Christine Custis, Jingying Yang, JT McHorse, Seth Reid, Sean McGregor, Sam Yoon, Catherine Olsson, and Roman Yampolskiy · 2021
Closest in time.