I Would Have Solved Alignment, But I Was Worried That Would Advance Timelines — LessWrong

The alignment community is ostensibly a group of people concerned about AI risk. Lately, it would be more accurate to describe it as a group of peopl…

x I Would Have Solved Alignment, But I Was Worried That Would Advance Timelines — LessWrong AI Capabilities AI Timelines Slowing Down AI AI Frontpage 126 I Would Have Solved Alignment, But I Was Worried That Would Advance Timelines by 307th 20th Oct 2023 10 min read 33 126 The alignment community is ostensibly a group of people concerned about AI risk. Lately, it would be more accurate to describe it as a group of people concerned about AI timelines. AI timelines have some relation to AI risk. Slower timelines mean that people have more time to figure out how to align future intelligent AIs, p

saved by

• Yudhister Joel Kumar
• Lawrence Feng

related reading

• Alignment remains a hard, unsolved problem — LessWronglesswrong.com
• “Alignment Engineering” vs. “Misalignment Science”lesswrong.com
• The Artificiality of Alignmentjoinreboot.org
• Defining alignment research — LessWronglesswrong.com
• Current AIs seem pretty misaligned to me — LessWronglesswrong.com
• Plans A, B, C, and D for misalignment risk — LessWronglesswrong.com
• The Case Against AI Control Research — LessWronglesswrong.com
• Differential acceleration of alignment-relevant capabilities is a bad bet — LessWronglesswrong.com
• Short Timelines Don't Devalue Long Horizon Research — LessWronglesswrong.com
• The case against AI alignment — LessWronglesswrong.com
• I think alignment work is more promising than control work — LessWronglesswrong.com
• A note about differential technological development — LessWronglesswrong.com