I’m someone new to the field, and I have a few ideas on it, namely penalizing a model for accessing more compute than it starts with (every scary AI story seems to start with the AI escaping containment and adding more compute to itself, causing an uncontrolled intelligence explosion). I’d like feedback on the ideas, but I have no idea where to post them or how to meaningfully contribute.
I live in America, so I don’t think I’ll be able to join the company you have in France, but I’d really like to hear where there are more opportunities to learn, discuss, formalize, and test out alignment ideas. As a company focused on this subject, is there a good place for beginners?
Probably the best place to get feedback as a beginner is AI Safety Support. They can also redirect you towards relevant programs, and they have a nice alignment slack.
As for your idea, I can give you quick feedback on my issues with this whole class of solutions. I’m not saying you haven’t thought about these issues, nor that no solution in this class is possible at all, just giving the things I would be wary of here:
How do you limit the compute if the AI is way smarter than you are?
Assuming that you can limit the compute, how much compute do you give it? Too little and it’s not competitive, leading many people to prefer alternatives without this limit; too much and you’re destroying the potential guarantees.
Even if there’s a correct and safe amount of compute to give for each task, how do you compute that amount? How much time and resources does it cost?
I’m someone new to the field, and I have a few ideas on it, namely penalizing a model for accessing more compute than it starts with (every scary AI story seems to start with the AI escaping containment and adding more compute to itself, causing an uncontrolled intelligence explosion). I’d like feedback on the ideas, but I have no idea where to post them or how to meaningfully contribute.
I live in America, so I don’t think I’ll be able to join the company you have in France, but I’d really like to hear where there are more opportunities to learn, discuss, formalize, and test out alignment ideas. As a company focused on this subject, is there a good place for beginners?
Thanks for your comment!
Probably the best place to get feedback as a beginner is AI Safety Support. They can also redirect you towards relevant programs, and they have a nice alignment slack.
As for your idea, I can give you quick feedback on my issues with this whole class of solutions. I’m not saying you haven’t thought about these issues, nor that no solution in this class is possible at all, just giving the things I would be wary of here:
How do you limit the compute if the AI is way smarter than you are?
Assuming that you can limit the compute, how much compute do you give it? Too little and it’s not competitive, leading many people to prefer alternatives without this limit; too much and you’re destroying the potential guarantees.
Even if there’s a correct and safe amount of compute to give for each task, how do you compute that amount? How much time and resources does it cost?