Lessons After a Couple Months of Trying to Do ML Research — LessWrong
I’m a 17 y/o who started doing transformer interpretability work around October 2021, mainly for the learning experience, but also with the goal of p…
x Lessons After a Couple Months of Trying to Do ML Research — LessWrong Scholarship & Learning Machine Learning (ML) Research Taste AI Practical Frontpage 72 Lessons After a Couple Months of Trying to Do ML Research by RowanWang 22nd Mar 2022 7 min read 8 72 I’m a 17 y/o who started doing transformer interpretability work around October 2021, mainly for the learning experience, but also with the goal of potentially finding something cool and interesting about transformers. I’m writing this post to consolidate some lessons I learned since then, and I hope that some of these ideas will be useful
Explore this link on the map →related reading
- An Opinionated Guide to ML Researchjoschu.net
- Tips for Empirical Alignment Research — AI Alignment Forumalignmentforum.org
- How To Become A Mechanistic Interpretability Researcher — AI Alignment Forumalignmentforum.org
- How To Become A Mechanistic Interpretability Researcher — LessWronglesswrong.com
- Zen and the Art of Machine Learning Researchblog.jxmo.io
- Lessons from My First 8 Years of Research | Tom Silvertomsilver.github.io
- Research Taste Exercises [rough note] -- colah's blogcolah.github.io
- vivek on X: "how to be good at research" / Xx.com
- How to win a best paper award (or, an opinionated take on how to do important research)nicholas.carlini.com
- Automated Weak-to-Strong Researcheralignment.anthropic.com
- ML Job Interviews: The Ultimate Guide – Silvia Saporasilviasapora.github.io
- How to Land a Frontier Lab Jobvladfeinberg.com