I'm leaving AI alignment – you better stay — LessWrong
lesswrong.com · 5,400 words · saved by 1 readers
This diagram summarizes the requirements for independent AI alignment research and how they are connected. …
x I'm leaving AI alignment – you better stay — LessWrong Postmortems & Retrospectives AI Personal Blog 152 I'm leaving AI alignment – you better stay by rmoehn 12th Mar 2020 6 min read 19 152 This diagram summarizes the requirements for independent AI alignment research and how they are connected. In this post I'll outline my four-year-long attempt at becoming an AI alignment researcher. It's an ‘I did X [including what I did wrong], and here's how it went’ post (see also jefftk's More writeups! ). I'm not complaining about how people treated me – they treated me well. And I'm not trying to co
related reading
- Tips for Empirical Alignment Research — AI Alignment Forumalignmentforum.org
- “Alignment Engineering” vs. “Misalignment Science”lesswrong.com
- Study Guide — LessWronglesswrong.com
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- Looking Back on My Alignment PhDturntrout.com
- Defining alignment research — LessWronglesswrong.com
- Thoughts on the impact of RLHF research — LessWronglesswrong.com
- AI safety undervalues founders — LessWronglesswrong.com
- The AI research job market shit show (and my experience)interconnects.ai
- The Field of AI Alignment: A Postmortem, and What To Do About It — LessWronglesswrong.com
- I Would Have Solved Alignment, But I Was Worried That Would Advance Timelines — LessWronglesswrong.com
- The Case Against AI Control Research — LessWronglesswrong.com