Productive Mistakes, Not Perfect Answers — LessWrong

This post is part of the work done at Conjecture. …

x Productive Mistakes, Not Perfect Answers — LessWrong Intellectual Progress (Society-Level) History & Philosophy of Science Practice & Philosophy of Science AI Frontpage 101 Productive Mistakes, Not Perfect Answers by adamShimi 7th Apr 2022 AI Alignment Forum 7 min read 11 101 Ω 40 This post is part of the work done at Conjecture . I wouldn’t bet on any current alignment proposal. Yet I think that the field is making progress and abounds with interesting opportunities to do even more, giving us a shot. Isn’t there a contradiction? No, because research progress so rarely looks like having a cl

related reading

• Alignment remains a hard, unsolved problem — LessWronglesswrong.com
• AGI Ruin: A List of Lethalities — LessWronglesswrong.com
• LessWronglesswrong.com
• Tips for Empirical Alignment Research — AI Alignment Forumalignmentforum.org
• The Field of AI Alignment: A Postmortem, and What To Do About It — LessWronglesswrong.com
• Focus on the places where you feel shocked everyone's dropping the ball — LessWronglesswrong.com
• PSA: Almost nobody is directly working on superintelligent alignment — LessWronglesswrong.com
• Abstract advice to researchers tackling the difficult core problems of AGI alignmenttsvibt.blogspot.com
• Can we safely automate alignment research? - Joe Carlsmithjoecarlsmith.com
• Shah and Yudkowsky on alignment failures — LessWronglesswrong.com
• A minimal viable product for alignment - by Jan Leikealigned.substack.com
• So You Want To Make Marginal Progress... — LessWronglesswrong.com