Full-time AGI Safety!

[Steven Byrnes]

Hi everyone!

I’m Steve Byrnes, a professional physicist in Boston. Y’all may know me as a regular blogger and commenter on this site. (Example post, Full list.)

Well, out of the blue, an exceptionally generous sponsor has granted me a grant to spend the next year full-time trying to advance AGI safety! (Eternal gratitude to Beth Barnes and the CEA donor lottery program!)

To make a long story short, my research plan is to immerse myself in the latest thinking about how the human brain works (i.e., what algorithm does it run?), and apply those insights to help move forward the discussion on AGI safety and strategy. (And conversely, to also help move forward the discussion of “What if we succeed?” within neuroscience.)

Until now I’ve been researching and blogging in little bits of time squeezed between work and kids. Not anymore! Starting today, I’m in full-time, all-out effort mode!

I know that this year is going to fly by far too quickly; I’m desperate to make the most of it. One thing that will help is lots of exchange of ideas! You can email me at [e-mail] if you want to see my research proposal, or discuss topics of interest, or just say hi! :-)

[Ben Pace]

Woop! I’m very pleased for you. I occasional plot about how to help people (including you-in-particular) to do this, and I’m very pleased that it has happened without my intervention! Beth continues to do good things, my appreciation to her.

I look forward greatly to your proportional increase in insights being posted to LessWrong :D

[adamShimi]

Welcome in the (for now) small family of people funded by Beth! Your research looks pretty cool, and I’m quite excited when seeing how different it is from mine. So Beth is funding quite a wide range of researchers, which is what makes most sense to me. :)

[MaxRa]

Congrats, those are great news! :) I’d love to read your proposal, will shoot you a mail.