Thanks @username and whoever directed the donation! (For a second I thought you were trying to pressure me into buying the book haha (which I did months ago).)

@DusanDNesic Thank you! We can't guarantee success but we can guarantee that we will work hard :)

@Rafe Thank you!

Responded to some points here: https://x.com/BerkeleyGenomic/status/1909101431103402245

@matiroy Thanks Mati!

@rahulxyz Thanks! Much appreciated. We'll make it happen. Maybe.

@Kaarel Thanks for your offer!

I'm unsure whether I agree with this strategically or not.

One consideration is that it may be more feasible to go really fast with [AGI alignment good enough to end acute risk] once you're smart enough, than to go really fast with convincing the world to effectively stop AGI creation research. The former is a technical problem you could, at least in principle, solve in a basement with 10 geniuses; the latter is a big messy problem involving myriads of people. I have substantial probability on "no successful AGI slowdown, but AGI is hard to make". In those worlds, where algorithmic progress continually burns the fuse on the intelligence explosion, a solution remains urgent, i.e. prevents more doom the sooner it comes.

But maybe good-enough AGI alignment is really extra super hard, which is plausible. Maybe effective world-coordination isn't as hard.

But I do mostly agree with this in terms of long-term vision.