Executive summary: A mathematical framework is proposed for giving AI systems an “artificial conscience” that can calculate the ethics of rights violations, incorporating factors like culpability, proportionality, and risk when determining if violating someone’s rights is justified in self-defense scenarios.
Key points:
Rights violations are quantified using equations that consider how much someone is “in harm’s way” and their culpability/blameworthiness for the situation.
Different levels of blameworthiness (from accidental to premeditated) affect how much someone’s rights can be violated in self-defense scenarios.
Proportionality matters—the response should be proportional to the threat, with different thresholds for property damage vs bodily harm vs loss of life.
For probabilistic threats, killing in self-defense may be justified if risk of death exceeds 0.1%, with rights gradually increasing as risk decreases below this threshold.
The framework distinguishes between personal self-defense and aided self-defense (helping others), with more latitude given for personal defense.
This comment was auto-generated by the EA Forum Team. Feel free to point out issues with this summary by replying to the comment, andcontact us if you have feedback.
Executive summary: A mathematical framework is proposed for giving AI systems an “artificial conscience” that can calculate the ethics of rights violations, incorporating factors like culpability, proportionality, and risk when determining if violating someone’s rights is justified in self-defense scenarios.
Key points:
Rights violations are quantified using equations that consider how much someone is “in harm’s way” and their culpability/blameworthiness for the situation.
Different levels of blameworthiness (from accidental to premeditated) affect how much someone’s rights can be violated in self-defense scenarios.
Proportionality matters—the response should be proportional to the threat, with different thresholds for property damage vs bodily harm vs loss of life.
For probabilistic threats, killing in self-defense may be justified if risk of death exceeds 0.1%, with rights gradually increasing as risk decreases below this threshold.
The framework distinguishes between personal self-defense and aided self-defense (helping others), with more latitude given for personal defense.
This comment was auto-generated by the EA Forum Team. Feel free to point out issues with this summary by replying to the comment, and contact us if you have feedback.