No offense, but It’s not obvious to me why communicating to a general audience could be a net positive. Exactly how do you expect this to help?
P.
Karma: 560
Most neural networks don’t have anything comparable to specialised brain areas, at least structurally, so you can’t see which areas light up given some stimulus to determine what that part does. You can do it with individual neurons or channels, though. The best UI I know of to explore this is the “Dataset Samples” option in the OpenAI Microscope, that shows which inputs activate each unit.
Please do! You can DM me their contact info, tell them about my accounts: either this one or my EA Forum one, or ask me for my email address.
Well, if he has, unbeknownst to me, already hired the “Terence Taos of the world” like he said on the podcast, that would be great, and I would move on to other tasks. But if he only has a regular alignment team, I don’t think either of us considers that to be enough. I’m just trying to convince him that it’s urgent and we can’t leave it for later.
I think I get it, but even if I didn’t now I know that’s how it sounds, and I think I know how to improve it. That will be for other mathematicians though (at least Maxim Kontsevich), see the edit to the post. Does the tone in the email to Demis seem like the right one to you?
I’ll rewrite it but I can’t just model other people after me. If I were writing it for someone like myself it would be a concise explanation of the main argument to make me want to spend time thinking about it followed by a more detailed explanation or links to further reading. As long as it isn’t mean I don’t think I would care if it’s giving me orders, begging for help or giving me information without asking for anything at all. But he at least already knows that unaligned AIs are a problem, I can only remind him of that, link to reading material or say that other people also think he should work on it.
But now the priority of that is lower, see the edit to the post. Do you think that the email to Demis Hassabis has similar problems or that it should stay like it is now?
Ok, I sent them an email.
Do you mean website links about his plan? I found nothing.
I’m still not changing the deadlines but I’ve received information that made me want to change the order.
Then do you think I should contact Jacob Steinhardt to ask him what I should write to interest Tao and avoid seeming like a crank?
There isn’t much I can do about SA other than telling him to work on the problem in his free time.
Unless something extraordinary happens I’m definitely not contacting anyone in politics. Politicians being interested in AGI is a nightmarish scenario and those news about Huawei don’t help my paranoia about the issue.
I might try that, but “community health” is not really what I’m optimising for. Maybe the name is misleading?
I was trying to rely on Tao’s trust in Demis’s judgement, since he is an AI researcher. Mentioning Eliezer is mainly so he has someone to contact if he wants to get hired.
I wanted his thinking to be “this competent entity has spent some of his computational resources verifying that it is important to solve this problem, and now that I’m reminded of that I should also throw mine at it”.
Is he truly mostly interested in what he considers to be mentally stimulating? Not in improving the world, or in social nonsense, or guaranteeing that his family is completely safe from all threats?
Then was including this link a bad idea? It gives examples of areas a mathematician might find interesting. And if not that, then what should I say? I’ve got nothing better. Do you know any technical introduction to alignment that he might like?
And about getting him to talk to other people, if anyone volunteers just DM me your contact information so that I can include it in the email (or reply directly if you don’t care about it being public). I mean, what else could I do?
That’s part of the point of the post, to coordinate so that fewer emails are sent. I asked if anyone tried something similar and asked people not to send their own emails without telling the rest of us.
[Question] Has anyone actually tried to convince Terry Tao or other top mathematicians to work on alignment?
Which should be followed by reading https://lukemuehlhauser.com/a-reply-to-wait-but-why-on-machine-superintelligence/
You wrote this twice:
From here, protecting humans and their values looks different than in the classic single/single scenario. On the other hand, it seems quite likely that there is a deep connection between safety issues in the “AI in a box” case, and in the ecosystems case.
From here, protecting humans and their values looks different than in the classic single/single scenario. On the other hand, it seems quite likely that there is a deep connection between safety issues in the “AI in a box” case, and in the ecosystems case.
Did you change your mind about Demis being reasonable or a petition being a good idea? And why? I’m considering sending him an email.
Even a little bit? Are you sure? https://www.lesswrong.com/posts/ido3qfidfDJbigTEQ/have-you-tried-hiring-people?commentId=wpcLnotG4cG9uynjC
Spoiler Warning. Tried hiding it with
>!and:::spoilerbut neither seems to work.For those unaware, this is a story (worth reading) about
anti-memes, ideas that cannot be spread, so researchers have a hard time working with them, not knowing they exist. So the point of the parent comment probably is thateven if an adequate AGI project existed we wouldn’t know about it.
What are they doing now?
There are already people taking care of that, see this question I asked recently.