Artificial Intelligence as a Positive and Negative Factor in Global Risk

By Eliezer Yudkowsky. 2006

Subfields: AI Ethics, Fairness & Society, Philosophy

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In AI Ethics, Fairness & Society

In Philosophy

Citations in the corpus

Conditional variance penalties and domain shift robustness (2017, background): “A different version of this story can be found in Yudkowsky (2008).”
Aligning Superintelligence with Human Interests: A Technical Research Agenda (2015, background): “Incorrectly speciﬁed superintelligent agents could be dangerous (Yudkowsky 2008).”
Agent Foundations for Aligning Machine Intelligence with Human Interests: A Technical Research Agenda (2017, background): “Because the stakes are so high, testing combined with a gut-level intuition that the system will continue to work outside the test environment is insufficient, even if the testing is extensive.”
Meaningful Human Control over Autonomous Systems: A Philosophical Account (2018, background): “More recently, the use of machine-learning systems has allegedly led to misclassification of enemy and friendly tanks because the training set had many images of enemy tanks with clouds and many of friendly tanks with cloudless skies or tracking higher or lower resolution (Yudowsky, 2006).”
Toward Idealized Decision Theory (2015, unknown): “A I] 7 J ul 2 01 5”
From Dependence to Causation (2016, background): “Therefore, the resulting neural network turned out to be a “weather classifier”, and its performance to detect tanks in new images was barely above chance (Yudkowsky, 2008).”
Corrigibility (2015, background): “…regard as erroneous goals would have an incentive to resist being corrected: general analysis of rational agents has suggested that almost all such agents are instrumentally motivated to preserve their preferences, and hence to resist attempts to modify them (Bostrom 2012; Yudkowsky 2008).”
Value Alignment or Misalignment - What Will Keep Systems Accountable? (2017, background): “…advancements, such as the idea of an impending singularity (Walsh 2016), but the risk assessment of AI systems as threats to develop beyond control (Yudkowsky 2008) has underwritten the recent launching of research programs of “alignment,” “safety engineering,” or containment (Taylor et al. 2016).”
Ethics of artificial intelligence and robotics (2020, background): “Generally, programming means rather than ends is dangerous (Yudkowsky 2008), but even programming ends can lead to undesired outcomes.”
The Ethics of Artificial Intelligence (2014, unknown): “…did not allow the programmers to envision the local behavior of Deep Blue—its response to a specific attack on its king—because Deep Blue computed the nonlocal game map, the link between a move and its possible future consequences, more accurately than the programmers could (Yudkowsky 2006).”
Deep Learning Based Vulnerability Detection: Are We There Yet? (2020, background): “[7] described an instance where US Army found out that a neural network”
Artificial General Intelligence: Concept, State of the Art, and Future Prospects (2009, methodology): “…from its current form (for discussion of various issues regarding the ethics of advanced AGI see (Goertzel and Pitt, 2012; Bostrom, 2014; Hibbard, 2012; Yudkowsky, 2008)) Anyone familiar with the current state of AGI research will ﬁnd it hard to suppress a smile at this ambitious list of…”
Guarding Against Adversarial Domain Shifts with Counterfactual Regularization (2017, background): “A different version of this story can be found in Yudkowsky (2008). variation corresponding to style features.”
Artificial Intelligence and Business Value: a Literature Review (2021, background): “Negative impacts due to AI use, however, are not restricted to biased outcomes, but include a number of other aspects such as black-box algorithms, lack of transparency and accountability, security concerns, as well as harm to society and the environment (Yudkowsky, 2008).”