Home | Substack

I think alignment is necessary, but not enough for AI to go well.

I think alignment is necessary, but not enough for AI to go well. By alignment, I mean us being able to get an AI to do what we want it to do, without it trying to do things basically nobody would want, such as amassing power to prevent its creators from turning it off.1 By AGI, I mean something that can do any economically valuable task that can be done through a computer about as well as a human can or better, such as scientific research. The necessity of alignment won’t be my focus here, so I will take it as a given. This notion of alignment is ‘‘value-free’’. It does not require…

related reading

• Alignment remains a hard, unsolved problem — LessWronglesswrong.com
• The Artificiality of Alignmentjoinreboot.org
• “Alignment Engineering” vs. “Misalignment Science”lesswrong.com
• The Case Against AI Control Research — LessWronglesswrong.com
• Neurotechnology is Critical for AI Alignmentmilan.cvitkovic.net
• Alignment & Succession: The Two Bars of Alignmentnosetgauge.com
• The case against AI alignment — LessWronglesswrong.com
• I think alignment work is more promising than control work — LessWronglesswrong.com
• What is AI alignment? - by Adam Jones - BlueDot Impactblog.bluedot.org
• The Alignment Problem — LessWronglesswrong.com
• Finally getting the depth of the AI alignment problempursuingreality.substack.com
• What Is The Alignment Problem? — LessWronglesswrong.com