Should We Fear Supersmart Robots?

By Stuart Russell. 2016

52 citations recorded by the source corpus.

How researchers see this paper

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

Deep Reinforcement Learning from Human Preferences (2017, background): “This difﬁculty underlies recent concerns about misalignment between our values and the objectives of our RL systems (Bostrom, 2014; Russell, 2016; Amodei et al., 2016).”
AI Safety Gridworlds (2017, background): “Expecting that more advanced versions of today’s AI systems are going to be deployed in realworld applications, numerous public figures have advocated more research into the safety of these systems (Bostrom, 2014; Hawking et al., 2014; Russell, 2016).”
The Off-Switch Game (2016, background): “Or, as (Russell 2016) puts it, you can’t fetch the coffee if you’re dead.”
Preventing undesirable behavior of intelligent machines (2019, background): “There has been growing interest in ensuring that machine learning algorithms are safe to use [8, 7, 64].”
On Ensuring that Intelligent Machines Are Well-Behaved (2017, background): “This framework does not address the problem of imbuing intelligent machines with a notion of morality or human-like values [Russell, 2016], nor the problem of avoiding undesirable behaviors that the user never considered [Amodei et al.”
AGI Safety Literature Review (2018, background): “This points to the risks with increasingly intelligent AGIs: If their goals are not aligned with ours, then there will likely be a point where their goals will be achieved to the loss of ours (Russell, 2016).”