About | Adam Scherlis
I’m an AI safety researcher (since 2020), with a particular interest in interpretability and related topics. Before that, I was a theoretical physicist. My research was primarily focused on building and testing models of dark matter in which it is composed of a very large number of very lightweight particles (e.g. axions). This blog is a mix of posts about AI alignment, physics, silly math puzzles, more “serious” math, and miscellaneous other topics. I like answering questions about ML, physics, math, etc! Contact me (Firstname@Lastname.com) if there’s anything in particular you want to know more about (or you noticed an error in a post, etc etc). Write a comment... Email me new posts Email me new comments Save my name, email, and website in this browser for the next time I comment. Δdocument.getElementById( "ak_js_1" ).setAttribute( "value", ( new Date() ).getTime() ); RSS - Posts Enter your email address to subscribe to this blog and receive notifications of new posts by email. Emai
About | Adam Scherlis Adam Scherlis Parameter Space: The Final Frontier Skip to content Home About Contact About I’m an AI safety researcher (since 2020), with a particular interest in interpretability and related topics. Before that, I was a theoretical physicist. My research was primarily focused on building and testing models of dark matter in which it is composed of a very large number of very lightweight particles (e.g. axions). This blog is a mix of posts about AI alignment, physics, silly math puzzles, more “serious” math, and miscellaneous other topics. I like answeri
Explore this link on the map →related reading
- LessWronglesswrong.com
- Vibe physics: The AI grad student \ Anthropicanthropic.com
- Problem Areas in Physics and AI Safety | Apart Researchapartresearch.com
- How To Become A Mechanistic Interpretability Researcher — AI Alignment Forumalignmentforum.org
- Nicholas Carlininicholas.carlini.com
- Automated Alignment Researchers: Using large language models to scale scalable oversight \ Anthropicanthropic.com
- Welcome!boydkane.com
- Perfectly Normalperfectlynormal.co.uk
- Interpretability Dreamstransformer-circuits.pub
- ARENA - AI Safety Curriculumlearn.arena.education
- The Iliad Intensive Course Materials — LessWronglesswrong.com
- How To Become A Mechanistic Interpretability Researcher — LessWronglesswrong.com