LESSWRONG
LW

All of novalinium's Comments + Replies

Carl Sagan, nuking the moon, and not nuking the moon

The little triangle guy in the back contamination figure reminds me of Haloarcula japonicus

Gram-negative, motile by flagella, triangular disk, ca. 2-5 µm x 0.2-0.5µm.

original discovery announcement, Takashina T et al (1990)

7eukaryote1y

"I want to indicate an alien microbe," I thought. "I'll just draw something with a distinctly microbial feature but otherwise so weird there's no way it could exist." Archaea have shown me what for once again. Thank you for introducing me to this odd fellow.

Video/animation: Neel Nanda explains what mechanistic interpretability is

novalinium2y32

A single word for this would be an animatic, probably.

2DanielFilan2y

I kinda guess that most people don't know what that means.

My experience at and around MIRI and CFAR (inspired by Zoe Curzi's writeup of experiences at Leverage)

novalinium3y70

If you're asking why I believe that they don't require presence, I've been interviewing with them and that's my understanding from talking with them. The first line of copy on their website is

Anthropic is an AI safety and research company that’s working to build reliable, interpretable, and steerable AI systems.

Sounds pretty much like a safety org to me.

7Vanessa Kosoy3y

Are you talking about "you can work from home and come to the office occasionally", or "you can live on a different continent"? I found no mention of existential risk on their web page. They seem to be a commercial company, aiming at short-to-mid-term applications. I doubt they have any intention to do e.g. purely theoretical research, especially if it has no applications to modern systems. So, what they do can still be meritorious and relevant to reducing existential risk. But, the context of this discussion is: can we replace all AI safety orgs by just one org. And, Anthropic is too specialized to serve such a role.

My experience at and around MIRI and CFAR (inspired by Zoe Curzi's writeup of experiences at Leverage)

novalinium3y40

Anthropic does not require consistent physical presence.

1Vanessa Kosoy3y

AFAICT, Anthropic is not an existential AI safety org per se, they're just doing a very particular type of research which might help with existential safety. But also, why do you think they don't require physical presence?