The AI Control Problem | the singularity is nearer

Put it out of your mind that the AI Control Problem is a mathematical problem with a mathematical solution. This is rationalist hogwash from the same people who, when pressed, won’t really tell you polyamory is the rational choice, but do subtlely believe that if you don’t agree about polyamory you are somehow less rational. Or perhaps just less Rational, but either way isn’t it obviously correct and can’t you see it?

Put it out of your mind that the AI Control Problem is a mathematical problem with a mathematical solution. This is rationalist hogwash from the same people who, when pressed, won’t really tell you polyamory is the rational choice, but do subtlely believe that if you don’t agree about polyamory you are somehow less rational. Or perhaps just less Rational, but either way isn’t it obviously correct and can’t you see it? Rationality is a wonderful tool, but it is only a tool. It can only deal in is, not in ought. This is a classic problem in moral philosophy . While I didn’t fully follow the inte

saved by

• Ellen Xu
• Justin Wang

related reading

• The Case Against AI Control Research — LessWronglesswrong.com
• The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
• What failure looks like — LessWronglesswrong.com
• Why AI Will Save the World | Andreessen Horowitza16z.com
• Selective Optimism: a critique of AI 2040 - by Richard Ngomindthefuture.info
• Center for a Stateless Society >> Review: Superintelligence — Paths, Dangers, Strategiesc4ss.org
• Existential Risk from AI: An Exposition for Mathematiciansalkjash.github.io
• There Is No A.I. | The New Yorkernewyorker.com
• The Problem — LessWronglesswrong.com
• Reading Listblog.redwoodresearch.org
• There is no AI riskgraymirror.substack.com
• Introduction to AI Control - by Sarah - BlueDot Impactblog.bluedot.org