Analysis of information sources in references of the Wikipedia article "Existential risk from artificial general intelligence" in English language version.
it's plausible to me that the main thing we need to get done is noticing specific circuits to do with deception and specific dangerous capabilities like that and situational awareness and internally-represented goals.
as long as they possess a sufficient level of intelligence, agents having any of a wide range of final goals will pursue similar intermediary goals because they have instrumental reasons to do so.
Nothing precludes sufficiently smart self-improving systems from optimising their reward mechanisms in order to optimisetheir current-goal achievement and in the process making a mistake leading to corruption of their reward functions.
50% of AI researchers believe there's a 10% or greater chance that humans go extinct from our inability to control AI.
For all these reasons, verifying a global relinquishment treaty, or even one limited to AI-related weapons development, is a nonstarter... (For different reasons from ours, the Machine Intelligence Research Institute) considers (AGI) relinquishment infeasible...
as long as they possess a sufficient level of intelligence, agents having any of a wide range of final goals will pursue similar intermediary goals because they have instrumental reasons to do so.
Nothing precludes sufficiently smart self-improving systems from optimising their reward mechanisms in order to optimisetheir current-goal achievement and in the process making a mistake leading to corruption of their reward functions.
It is fantasy to suggest that the accelerating development and deployment of technologies that taken together are considered to be A.I. will be stopped or limited, either by regulation or even by national legislation.
As if losing control to Chinese minds were scarier than losing control to alien digital minds that don't care about humans. [...] it's clear by now that the space of possible alien minds is vastly larger than that.
It is therefore no surprise that according to the most recent AI Impacts Survey, nearly half of 731 leading AI researchers think there is at least a 10% chance that human-level AI would lead to an "extremely negative outcome," or existential risk.
For all these reasons, verifying a global relinquishment treaty, or even one limited to AI-related weapons development, is a nonstarter... (For different reasons from ours, the Machine Intelligence Research Institute) considers (AGI) relinquishment infeasible...
It is fantasy to suggest that the accelerating development and deployment of technologies that taken together are considered to be A.I. will be stopped or limited, either by regulation or even by national legislation.
as long as they possess a sufficient level of intelligence, agents having any of a wide range of final goals will pursue similar intermediary goals because they have instrumental reasons to do so.