Fetching the paper…
Reading the bibliography…
While several recent works have identified societal-scale and extinction-level risks to humanity arising from artificial intelligence, few have attempted an {\em exhaustive taxonomy} of such risks.
Preferences implicit in the state of the world
Shah, R., D. Krasheninnikov, J. Alexander, P. Abbeel, and A. Dragan (2019) · 1902
Earlier work this paper cites.
Learning gentle object manipulation with curiosity-driven deep reinforcement learning
Huang, S. H., M. Zambelli, J. Kay, M. F. Martins, Y. Tassa, P. M. Pilarski, and R. Hadsell (2019) · 1903
Earlier work this paper cites.
Literal or pedagogic human? analyzing human model misspecification in objective learning
Milli, S. and A. D. Dragan (2019) · 1903
Earlier work this paper cites.
Semenova, L. and C. Rudin (2019) · 1908
Earlier work this paper cites.
R.U.R. (Rossum’s Universal Robots)
Capek, K. (1920) · 1920
Earlier work this paper cites.
Some moral and technical consequences of automation
Wiener, N. (1960) · 1960
Earlier work this paper cites.
Launch control safety study
Watson, H. A. et al. (1961) · 1961
Earlier work this paper cites.
Fault tree analysis- the study of unlikely events in complex systems(fault tree analysis as tool to identify component failure as probable cause of undesired event in complex system)
Mearns, A. (1965) · 1965
Earlier work this paper cites.
Speculations concerning the first ultraintelligent machine
Good, I. J. (1966) · 1966
Earlier work this paper cites.
Fault tree analysis, methods, and applications: a review
Lee, W.-S., D. L. Grosh, F. A. Tillman, and C. H. Lie (1985) · 1985
Earlier work this paper cites.
Super-intelligent machines
Hibbard, B. (2001) · 2001
Earlier work this paper cites.
Identifying the effect of unemployment on crime
Raphael, S. and R. Winter-Ebmer (2001) · 2001
Earlier work this paper cites.
Can we obfuscate programs
Barak, B. (2002) · 2002
Earlier work this paper cites.
The complexity of decentralized control of markov decision processes
Bernstein, D. S., R. Givan, N. Immerman, and S. Zilberstein (2002) · 2002
Earlier work this paper cites.
Intelligent Machinery, A Heretical Theory (c.1951). Reprinted in The Essential Turing , by B. Jack Copeland., 2004
Turing, A. (1951b) · 2004
Earlier work this paper cites.
Regulatory capture: A review
Dal Bó, E. (2006) · 2006
Earlier work this paper cites.
Artificial intelligence as a positive and negative factor in global risk
Yudkowsky, E. et al. (2008) · 2008
Earlier work this paper cites.
The social agency problem
Shapiro, D. G. (2011) · 2011
Earlier work this paper cites.
Artificial intelligence and the end of the human era
Barrat, J. (2013) · 2013
Earlier work this paper cites.
Preventing regulatory capture: Special interest influence and how to limit it
Carpenter, D. and D. A. Moss (2013) · 2013
Earlier work this paper cites.
Trees trap ants into sweet servitude
Ed Yong (2013) · 2013
Cited alongside, same era.
Superintelligence: Paths, Dangers, Strategies
Bostrom, N. (2014) · 2014
Cited alongside, same era.
White paper: Value alignment in autonomous systems
Russell, S. (2014) · 2014
Cited alongside, same era.
Aligning superintelligence with human interests: A technical research agenda
Soares, N. and B. Fallenstein (2014) · 2014
Cited alongside, same era.
Taxonomy of pathways to dangerous ai
Yampolskiy, R. V. (2015) · 2015
Cited alongside, same era.
Concrete problems in AI safety
Amodei, D., C. Olah, J. Steinhardt, P. Christiano, J. Schulman, and D. Mané (2016) · 2016
Human compatible: Artificial intelligence and the problem of control
Russell, S. (2019) · 2019
Later among the works it cites.
Thinking about risks from ai: accidents, misuse and structure
Zwetsloot, R. and A. Dafoe (2019) · 2019
Later among the works it cites.
Closing the AI accountability gap: defining an end-to-end framework for internal algorithmic auditing
Raji, I. D., A. Smart, R. N. White, M. Mitchell, T. Gebru, B. Hutchinson, J. Smith-Loud, D. Theron, and P. Barnes (2020) · 2020
Later among the works it cites.
Conservative agency via attainable utility preservation
Turner, A. M., D. Hadfield-Menell, and P. Tadepalli (2020) · 2020
Later among the works it cites.
Regulation of the european parliament and of the council: Laying down harmonised rules on artificial intelligence (artificial intelligence act) and amending certain union legislative acts
European Commission (2021) · 2021
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Cited alongside, same era.
Cooperative inverse reinforcement learning
Hadfield-Menell, D., S. J. Russell, P. Abbeel, and A. Dragan (2016) · 2016
Cited alongside, same era.
Indistinguishability obfuscation from ddh-like assumptions on constant-degree graded encodings
Lin, H. and V. Vaikuntanathan (2016) · 2016
Cited alongside, same era.
Alignment for advanced machine learning systems
Taylor, J., E. Yudkowsky, P. LaVictoire, and A. Critch (2016) · 2016
Cited alongside, same era.
Low impact artificial intelligences
Armstrong, S. and B. Levinstein (2017) · 2017
Cited alongside, same era.
Critch, A. (2017) · 2017
Cited alongside, same era.
Servant of many masters: Shifting priorities in pareto-optimal sequential decision-making
Critch, A. and S. Russell (2017) · 2017
Cited alongside, same era.
China’s new AI governance initiatives shouldn’t be ignored
Sheehan, M. (2021) · 2021
Later among the works it cites.
An open agency architecture for safe transformative AI
Dalrymple, D. A. (2022) · 2022
Later among the works it cites.
Ai risk management framework: Initial draft
National Institute of Standards and Technology (2022) · 2022
Later among the works it cites.
Compute accounting principles can help reduce AI risks
US Senate Subcommittee on Privacy, Technology, and the Law (2022) · 2022
Later among the works it cites.
Blueprint for an AI Bill of Rights: Making Automated Systems Work for the American People
White House (2022) · 2022
Later among the works it cites.
How rogue AIs may arise
Bengio, Y. (2023) · 2023
Closest in time.
Untitled video statement calling for articulation of concrete cases of harm and extinction
Bengio, Y. and A. Ng (2023) · 2023
Closest in time.
Statement on AI risk
Center for AI Safety (2023) · 2023
Closest in time.
Measures for the management of generative artificial intelligence services (draft for comment)
Cyberspace Administration of China (2023) · 2023
Closest in time.
Translation: Measures for the management of generative artificial intelligence services (draft for comment)
Huang, S., H. Toner, Z. Haluza, and R. Creemers (2023) · 2023
Closest in time.
Artificial intelligence challenges and opportunities for the department of defense
Matheny, J. (2023) · 2023
Closest in time.
President Biden and U.K. Prime Minister Rishi Sunak hold news conference at White House | full video
Sunak, R. and J. Biden (2023) · 2023
Closest in time.
US Senate Judiciary Committee Hearing on Oversight of A.I. (video footage)
US Senate Judiciary Committee (2023) · 2023
Closest in time.
Oversight of A.I.: Rules for Artificial Intelligence
US Senate Subcommittee on Privacy, Technology, and the Law (2023) · 2023
Closest in time.