A note about differential technological development — LessWrong
Quick note: I occasionally run into arguments of the form "my research advances capabilities, but it advances alignment more than it advances capabil…
x A note about differential technological development — LessWrong 2022 MIRI Alignment Discussion AI Curated 200 A note about differential technological development by So8res 15th Jul 2022 AI Alignment Forum 7 min read 34 200 Ω 67 Quick note: I occasionally run into arguments of the form "my research advances capabilities, but it advances alignment more than it advances capabilities, so it's good on net". I do not buy this argument, and think that in most such cases, this sort of research does more harm than good. (Cf. differential technological development .) For a simplified version of my mod
Explore this link on the map →related reading
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- Short Timelines Don't Devalue Long Horizon Research — LessWronglesswrong.com
- AGI Ruin: A List of Lethalities — LessWronglesswrong.com
- I Would Have Solved Alignment, But I Was Worried That Would Advance Timelines — LessWronglesswrong.com
- Preparing for the Intelligence Explosionforethought.org
- Differential acceleration of alignment-relevant capabilities is a bad bet — LessWronglesswrong.com
- Can we safely automate alignment research? - Joe Carlsmithjoecarlsmith.com
- Defining alignment research — LessWronglesswrong.com
- PSA: Almost nobody is directly working on superintelligent alignment — LessWronglesswrong.com
- Sequent: Scale and Automation for Higher Confidence in Alignment — Sequentsequent.org
- Distillation of Neurotech and Alignment Workshop January 2023 — LessWronglesswrong.com
- The Case Against AI Control Research — LessWronglesswrong.com