Thanks a lot for this article!
I just wanted to link to Lukas Gloor’s new paper on Fail-Safe AI, which discusses the reduction of “quality future-risks” in the context of AI safety. It turns out that there might be interventions that are less directed at achieving a perfect outcome, but instead try to avoid the worst outcomes. And those interventions might be more tractable (because they don’t aim at such a tiny spot in value-space) and more neglected than other work on the control problem.
https://foundational-research.org/wp-content/uploads/2016/08/Suffering-focused-AI-safety.pdf
Thanks a lot for this article! I just wanted to link to Lukas Gloor’s new paper on Fail-Safe AI, which discusses the reduction of “quality future-risks” in the context of AI safety. It turns out that there might be interventions that are less directed at achieving a perfect outcome, but instead try to avoid the worst outcomes. And those interventions might be more tractable (because they don’t aim at such a tiny spot in value-space) and more neglected than other work on the control problem. https://foundational-research.org/wp-content/uploads/2016/08/Suffering-focused-AI-safety.pdf