x

LESSWRONG

LW

AugustMurr — LessWrong

AugustMurr

AugustMurr

Message

I'm August Murr, I'm a self-taught AI safety researcher focused on alignment, safety, and governance.

More of my work and working drafts: github.com/August-murr

If you want to connect:
moh.murr@gmail.com
LinkedIn

8

1

2mo

AugustMurr

I'm August Murr, I'm a self-taught AI safety researcher focused on alignment, safety, and governance.

More of my work and working drafts: github.com/August-murr

If you want to connect:
moh.murr@gmail.com
LinkedIn

AI Safety Is Testing the Wrong Environment

The Lab Problem in AI Safety There's something that doesn't sit right with me about where alignment research happens. So much research, so many researchers, ideas, experiments, but the environment makes no sense. Almost all of it takes place in the same setting: one AI, one user, a chat interface,...