Thomas Broadley

Replacing Guilt is a book by Nate Soares, a collection of blog posts about replacing guilt-based motivation with something stronger.

Last June or July, I switched from working primarily on METR's AI evaluations infrastructure to working on a particular research project.

I.

Even in Berkeley, we get less than ten hours of sunlight a day in January.

About a month ago, METR published a paper called "RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts".

My wife and I just moved to Berkeley, California.

METR just open-sourced Vivaria, our platform for writing AI evals and running agents on them.

At METR, I'm trying to reduce existential risk from artificial intelligence by helping to measure the autonomous capabilities of language model agents.

In the last couple of weeks, I've given two talks on the subject of dangerous capabilities evaluations for AI, one to Toronto AI Safety and the other to the Wisconsin AI Safety Initiative.

OpenSSH (the book) says this about SSH multiplexing: Multiplexing is the ability to send more than one signal over a single line or connection.

A little over two months ago, I left my job at Faire to figure out how I could help reduce existential risk from AI.

In preparation for moving to the US, I purchased traveller's health insurance for my wife and myself.

Cross-posted to LessWrong.

In just over a week, I’m quitting my job as a software developer at Faire.

Last week, I created a chatbot that answers questions about AI safety.

I started learning Vietnamese on Duolingo three months ago.

A few days ago, a coworker and I played around with ChatGPT for 10 minutes.

I’ve written a lot of Kotlin code over the past three years, but I didn’t get Kotlin’s in and out keywords… until yesterday.

I’m working through Hammertime, a 30-day program of instrumental rationality exercises.

I subscribe to about 100 RSS feeds and one email newsletter: Money Stuff.