LessWrong 2.0 Reader

Privacy of communities isn't a solvable problem in general, as soon as your community is large enough to compete with the adversary, it's large enough and conspicuous enough that the adversary will pay attention to it and send in spies and extract leaks.

I disagree with this in theory as a long-term concern, but yes in practice the methods to have privacy of communities haven't been implemented or tested at all, and I agree with the general sentiment that it isn't worth the steep drawbacks of privacy to protect secrets, which does unfortunately make me dislike the post due to it's strength of recommendations.

So while I could in theory disagree with you, in practice right now I mostly have to agree with the comment that there will not be such an infrastructure for private alignment ideas.

Also to touch on something here that isn't too relevant and could be considered a tangent:

If your acceptable lower limit for basically anything is zero you wont be allowed to do anything, really anything.

This is why perfectionism is such a bad thing, and why you need to be able to accept that failure happens. You cannot have 0 failures IRL.

## Discretize B ## # [B,N] [E->N] [B,E] B = layer.W_B(x[b,l]) # no bias

Shouldn't this be x[:,l] instead of x[b,l]?

There never will be an infrastructure for this.

I should be less resolute about this. It would kind of be my job to look for a design that could do it.

One thing we've never seen is a system where read receipts are tracked and analyzed on the global level and read permissions are suspended and alerts are sent to admins if an account is doing too many unjustified reads.
This would prevent a small number of spies from extracting a large number of documents.
I suppose we could implement that today.

If there are actual crimes going on, I'd imagine the police should be called.

If a student is genuinely acting in bad faith - attending a class and ruining it for their peers - then they should be removed from the class and sent to a counselor/social worker.

Otherwise, "disruptive" is a difficult thing to pin down when there's no actual instruction to be interrupting.

The EA SummerCamp takes place the next weekend

I've not been to any of these, but would like to. Is there any info up yet for this years EA SummerCamp?

strictly weaker

add "than Condorcet" in this sentence since its only implied but not said

The LessWrong Review [? · GW] runs every year to select the posts that have most stood the test of time. This post is not yet eligible for review, but will be at the end of 2024. The top fifty or so posts are featured prominently on the site throughout the year. Will this post make the top fifty?

This seems contrary to how much of science works. I expect if people stopped talking publicly about what they're working on in alignment, we'd make much less progress, and capabilities would basically run business as usual.

The sort of reasoning you use here, and that my only response to it basically amounts to "well, no I think you're wrong. This proposal will slow down alignment too much" is why I think we need numbers to ground us.

You think that studying agency and infrabayesianism wont make small contributions to capabilities? Even just saying "agency" in the context of AI makes capabilities progress.

"So where do I privately share such research?" — good question! There is currently no infrastructure for this.

This is why I currently think you're completely wrong about this. There never will be an infrastructure for this. Privacy of communities isn't a solvable problem in general, as soon as your community is large enough to compete with the adversary, it's large enough and conspicuous enough that the adversary will pay attention to it and send in spies and extract leaks. If you make it compartmented enough to prevent leaks/weed out the spies, it wont have enough intellectual liveliness to solve the alignment problem.

There is nothing that makes differentially helping capabilities "fine if you're only differentially helping them a little bit".

If your acceptable lower limit for basically anything is zero you wont be allowed to do anything, really anything. You have to name some quantity of capabilities progress that's okay to do before you'll be allowed to talk about AI in a group setting.