MATS Applications Open (Due Aug 29) — Neel Nanda

I am looking for people who want to be supervised by me to write a mech interp paper. Apply here now ! Due Aug 29

TLDR I am looking for people who want to be supervised by me to write a mech interp paper. Apply here now! Due Aug 29 Application task: Spend ~12 hours (max 20) working on a mechanistic interpretability research problem of your choice, and send me a write-up + executive summary of what you learned. (See advice, details, past examples and recommended problems in the doc) The top ~32 candidates will do a 5 week paid online exploration phase (Sept 29 - Oct 31) ending in a 2 week research sprint in pairs. Expect unstructured, self-driven learning The ~8 exploration phase candidates with the…

saved by

• ic c

related reading

• How To Become A Mechanistic Interpretability Researcher — AI Alignment Forumalignmentforum.org
• How To Become A Mechanistic Interpretability Researcher — LessWronglesswrong.com
• A Pragmatic Vision for Interpretability — AI Alignment Forumalignmentforum.org
• An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2 — AI Alignment Forumalignmentforum.org
• An Opinionated Guide to ML Researchjoschu.net
• MATS 9 Retrospective & Advice — LessWronglesswrong.com
• Neel Nanda on Mechanistic Interpretability: Progress, Limits, and Paths to Safer AI — EA Forumforum.effectivealtruism.org
• A Pragmatic Vision for Interpretability — LessWronglesswrong.com
• An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2 — AI Alignment Forumalignmentforum.org
• ML Job Interviews: The Ultimate Guide – Silvia Saporasilviasapora.github.io
• Giang Nguyen (@giangnguyen2412) on Xx.com
• Aryaman Arora (@aryaman2020) on Xx.com