TheManxLoiner

[Today is Day 13 of an ongoing 30-day microblogging challenge. It was initiated by Zoe Isabel Senón. You can see who is participating and also join in via this doc.] In my post about a conversation with a capabilities research, I ended with this thought: > I believe that people...

I was at a house party hosted by an AI Safety friend of mine. I join a conversation midway, where my friend is saying that doing capabilities research at frontier lab is evil, given the catastrophic risks. Nothing out of the ordinary, until I find out the person who they...

Introduction The aim of this post is to share a quick attempt at grokking the conceptual ideas that lie behind the notion of J-space and how it is calculated in the paper Verbalizable Representations Form a Global Workspace in Language Models. Specifically, I am trying to understand Section 2.1 of...

Here is my advice for people interested in research management (RM). It’s an info dump, but you should at least skim all the materials if you are seriously considering this for your career. What is RM? * RM means different things in different places. Ensure you check what the work...

Last week, I attended a talk ‘AI as a social technology’ by Henry Farell (HF) at the Blavatnik School of Government in Oxford. In this post, I list various thoughts or recollections I have. If I had more time, I would create a more coherent flowing narrative, but I’d rather...

Crossposted on my personal blog. This is post number 16 in my second attempt at doing Inkkaven in a day, i.e. to write 30 blogposts in a single day. MATS is an organization that pairs up-and-coming AI Safety researchers (who I call participants) with the world’s best (this is not...

TLDR I propose restructuring the current ARENA program, which primarily focuses on contained exercises, into a more scalable and research-engineering-focused model consisting of four one-week research sprints preceded by a dedicated "Week Zero" of fundamental research engineering training. The primary reasons are: * The bottleneck for creating good AI safety...