Post 50: Good Research Takes are Not Sufficient for Good Strategic Takes — Neel Nanda
Having a good research track record is some evidence of good big-picture takes about AGI, but it's weak evidence. Strategic thinking is hard, and requires different skills. But people often conflate these skills, leading to excessive deference to researchers in the field, without evidence that that
Post 50: Good Research Takes are Not Sufficient for Good Strategic Takes Mar 22 Written By Neel Nanda TL;DR Having a good research track record is some evidence of good big-picture takes about AGI, but it's weak evidence. Strategic thinking is hard, and requires different skills. But people often conflate these skills, leading to excessive deference to researchers in the field, without evidence that that person is good at strategic thinking specifically. Introduction I often find myself giving talks or Q&As about mechanistic interpretability research. But inevitably, I'll get questions about t
saved by
related reading
- Tips for Empirical Alignment Research — AI Alignment Forumalignmentforum.org
- Strategic Tastejason.ml
- A model of research skill — LessWronglesswrong.com
- “Alignment Engineering” vs. “Misalignment Science”lesswrong.com
- Post 47: How I Formed My Own Views About AI Safety - Neel Nandaneelnanda.io
- How Can Interpretability Researchers Help AGI Go Well? — AI Alignment Forumalignmentforum.org
- The Case Against AI Control Research — LessWronglesswrong.com
- Deferral is a skilllawsen.substack.com
- How do we (more) safely defer to AIs? — LessWronglesswrong.com
- The Universe from an Intentional Stancecasparoesterheld.com
- How To Think Real Good | Meta-rationalitymetarationality.com
- Neel Nanda on Mechanistic Interpretability: Progress, Limits, and Paths to Safer AI — EA Forumforum.effectivealtruism.org