In 10 seconds

I'm a self-taught programmer and math geek. My main goals are to make AI go well, and become stronger.

I'm an autodidact (I was unschooled) and love learning things quickly.

Now

From April 7th - June 1st I'm doing part-time alignment research in Berkeley while spending the rest of my time becoming stronger. Would love to meet up if you're in the area!

TLDR of Life plan

I have two primary goals, self-improvement and doing good. Because I think future AI systems getting out of human control have a >10% chance of causing an extinction-level event, I do work to understand how we can better control generally intelligent AI systems.

My current plan is roughly:

  1. Self-improve a bunch, study a bunch, deliberately practice a bunch
  2. Alignment research
  3. ????
  4. Save the world (in the branches where AI goes wrong by default)

In my culture

You basically can't offend me, I operate by Crocker's rules, meaning I'm fine with people optimizing their messages for information content over tact.

You can ask me for things. If there's something that's easy for me and hard for you go ahead and ask. I am capable of saying no to things, and I enjoy helping people. In particular: