Hey, there is a common plan I hear that maybe you’d like to respond to directly.
It goes something like this: “I’ll go work at a top AI lab as an engineer, build technical skills, and I care about safety so I can push a bit towards safe decisions, or push a lot if it’s important, overall it seems good to have people there who care about safety like me. I don’t have a good understanding of how to do alignment but there are some people I trust”
If you’re willing to reply to this, I’ll probably refer people directly to your answer sometimes
I think that for many people (but not everyone) and for many roles they might work in (but not all roles), this is a reasonable plan.
Most importantly, I think it’s true that working at a top AI lab as an engineer is one of the best ways to build technical skills (see the section above on “it’s often excellent career capital”).
I’m more sceptical about the ability to push towards safe decisions (see the section above on “you may be able to help labs reduce risks”).
The right answer here depends a lot on the specific role. I think it’s important to remember than not all AI capabilities work is necessarily harmful (see the section above on “you might advance AI capabilities, which could be (really) harmful”), and that top AI labs could be some of the most positive-impact organisations in the world (see the section above on “labs could be a huge force for good—or harm”). On the other hand, there are roles that seem harmful to me (see “how can you mitigate the downsides of this option”).
I’m not sure of the relevance of “having a good understanding of how to do alignment” to your question. I’d guess that lots of knowing “how to do alignment” is being very good at ML engineering or ML research in general, and that working at a top AI lab is one of the best ways to learn those skills.
Hi! Thanks for your answer. TL;DR: I understand and don’t have further questions on this point
What I mean by “having a good understanding of how to do alignment” is “being opinionated about (and learning to notice) which directions make sense, as opposed to only applying one’s engineering skills towards someone else’s plan”.
I think this is important if someone wants to affect the situation from inside, because the alternative is something like “trust authority”.
But it sounds like you don’t count on “the ability to push towards safe decisions” anyway
Hey, there is a common plan I hear that maybe you’d like to respond to directly.
It goes something like this: “I’ll go work at a top AI lab as an engineer, build technical skills, and I care about safety so I can push a bit towards safe decisions, or push a lot if it’s important, overall it seems good to have people there who care about safety like me. I don’t have a good understanding of how to do alignment but there are some people I trust”
If you’re willing to reply to this, I’ll probably refer people directly to your answer sometimes
Hi Yonatan,
I think that for many people (but not everyone) and for many roles they might work in (but not all roles), this is a reasonable plan.
Most importantly, I think it’s true that working at a top AI lab as an engineer is one of the best ways to build technical skills (see the section above on “it’s often excellent career capital”).
I’m more sceptical about the ability to push towards safe decisions (see the section above on “you may be able to help labs reduce risks”).
The right answer here depends a lot on the specific role. I think it’s important to remember than not all AI capabilities work is necessarily harmful (see the section above on “you might advance AI capabilities, which could be (really) harmful”), and that top AI labs could be some of the most positive-impact organisations in the world (see the section above on “labs could be a huge force for good—or harm”). On the other hand, there are roles that seem harmful to me (see “how can you mitigate the downsides of this option”).
I’m not sure of the relevance of “having a good understanding of how to do alignment” to your question. I’d guess that lots of knowing “how to do alignment” is being very good at ML engineering or ML research in general, and that working at a top AI lab is one of the best ways to learn those skills.
Hi! Thanks for your answer. TL;DR: I understand and don’t have further questions on this point
What I mean by “having a good understanding of how to do alignment” is “being opinionated about (and learning to notice) which directions make sense, as opposed to only applying one’s engineering skills towards someone else’s plan”.
I think this is important if someone wants to affect the situation from inside, because the alternative is something like “trust authority”.
But it sounds like you don’t count on “the ability to push towards safe decisions” anyway