Aspiring EA-adjacent trying to make the singularity further away
Pato
Karma: 129
Cool! I just hope that in the future you crosspost all the posts here. I like the forum and don’t like to have to check different external blogs.
I agree with some points of the post but don’t like at all how it defines the things that cost you the less as “True values” and are recommending people to follow them.
As an agnostic on what is the best way of defining values and how good is for people to do the things they are the most motivated to do, I want to remind people that you could define what your “True values” are as the things you do even tho they cost you more energy; and that doing them could be better.
So I think we agree that it seems good to find the right balance between following costly and not costly values, but calling some of them the True ones seems to imply that you should focus on or do only them.
easily best intro to agi safety
Meat with that label comes from farms that have stricter regulations for mutilation (dehorning, castration, debeaking, tail docking) and better air quality. The animals on those farms have more space and barn enrichments (e.g. toys, animal brushes, hay) and fewer diseases. Suppose meat with this animal welfare label costs 50% more than meat without an animal welfare label, and animal suffering for meat with the animal welfare label is half the amount of animal suffering for meat without a label.
Only half the suffering? With that description I was thinking on lives with a lot less suffering. And even worth living. I don’t know much about animal welfare so where that suffering is coming from?
I just listen to these type of videos as podcasts and don’t read transcripts.
Thanks! I think I understood everything now and in a really quick read.
Thank you a lot! I wasn’t expecting a summary, I wrote it so maybe you could have it as a consideration for future posts, so I guess I should have written less simple.
Can you give me an example of EA using bad epistemic standards and an example of EA using good epistemic standards?
Personally I have trouble understanding this post. Could you write simpler?
I agree that maybe people don’t get it (like kinda me) but I think both things, posts and comments, should have it or neither.
When people want an apology, they expect you to say that you’re sorry and you were wrong. But I have also read in response of every apology ever written or said in the history of the internet that the wrong doers in question don’t actually take responsibility for their actions and I never understood what they meant for that. Do they expect the person to punish themselves? To say “I take responsibility for my actions”? To not express their reasoning behind their actions? I honestly don’t know.
Oh, I didn’t know that the field was so against AI X-risks. Because when I saw this https://aiimpacts.org/what-do-ml-researchers-think-about-ai-in-2022/ 5-10% of X-risks seemed enough to take them seriously. Is that survey not representative? Or is there a gap between people recognizing the risks and giving them legitimacy?
Interesting.
I’m not sure I understood the first part and what f(A,B) is. In the example that you gave B is only relevant with respect of how much it affects A (“damage the reputability of the AI risk ideas in the eye of anyone who hasn’t yet seriously engaged with them and is deciding whether or not to”). So, in a way you are still trying to maximize |A| (or probably a subset of it: people who can also make progress on it (|A’|)). But in “among other things” I guess that you could be thinking of ways in which B could oppose A, so maybe that’s why you want to reduce it too. The thing is: I have problems visualizing most of B opposing A and what that subset (B’) could even be able to do (as I said, outside reducing |A|). I think that that is my biggest argument, that B’ is a really small subset of B and I don’t fear them.
Now, if your point is that to maximize |A| you have to keep in mind B and so it would be better to have more ‘legitimacy’ on the alignment problem before making it viral you are right. So is there progress on that? Is the community building plan to convert authorities in the field to A before reaching the mainstream then?
Also are people who try to disprove the alignment problem in B? If that’s the case I don’t know if our objective should be to maximize |A’|. I’m not sure if we can reach a superintelligence with AI, so I don’t know if it wouldn’t be better to think about maximize the people trying to solve OR dissolve the alignment problem. If we consider that most people probably wouldn’t feel strongly about one side of the other (debatable), then I don’t think is that big of a deal bringing the discussions more to the mainstream. If AI risk arguments include that not matter how uncertain researchers are about the problem giving what’s at stake we should lower the chances, then I even see B and B’ smaller. But maybe I’m too optimistic/ marketplacer/ memer.
Lastly, the maximum size of A is smaller the shorter the timelines. Are people with short timelines the ones trying to reach the most people in the short term?
I think EA has the resources to make the alignment problem viral or at least in STEM circles. Wouldn’t that be good? I’m not asking if it would be an effective way of doing good, just a way.
Because I’m surprise that not even AI doomers seem to be trying to reach the mainstream.
Wow, I didn’t expected a response. I didn’t know shortforms were that accessible and I thought I was just rambling in my profile. So I should clarify that when I say “what we actually want” I mean our actual terminal goals (if we have those).
So what I’m saying is that we are not training AIs or creating any other technology to do our terminal goals but to do other things (of course they’re specific because they don’t have high capabilities). But in the moment that we create something that can take over the world, all of the sudden the fact that we didn’t create it to do our terminal goals becomes a problem.
I’m not trying to explain why present technologies have failures, but that misalignment is not something that appears with the creation of powerful AIs but that that is the moment when it becomes a problem, and that’s why you have to create it with a different mentality than any other technology.
I’m still learning basic things about AI Alignment, but it seems to me that all AIs (and other technologies) already don’t give us exactly what we want but we don’t call that outer misaligned because they are not “agentic” (enough?). The thing is that I don’t know if there’s a crucial? onthologic? property that make something agentic really, I think it could be just some type of complexity that we give a lot of value to.
And also ML system are inner misaligned in a way because they can’t generalize to everything from examples and we can see that when we don’t like the results to a particular task that they give us. I don’t think misaligned is maybe the word for these technologies, but really the important thing is that they don’t do what we want them to do.So the question about AI risk really is: are we going to build a superintelligent technology? Because that is the significant difference with the previous technologies. If that’s the case, we are not going to be the ones influencing the future the most, building little by little what we actually want and stopping the use of technologies whenever they aren’t useful. We are going to be the ones turned off.
Pato’s Quick takes
I created an account and I’m pretty sure I still can’t change or add anything.
I don’t agree with the first statement neither understand what are you arguing for or against.
Why do you think this? I infer for what I’ve seen written in other posts and comments that this is a common belief but I don’t find the reasons why.
The fact that there are specific really difficult problems with aligning ML systems doesn’t mean that the original really difficult problem with finding and specifying the objectives that we want for a superintelligence were solved.
I hate it because it makes it seems like alignment is a technical problem that can be solved by a single team and as you put it in your other post we should just race and win against the bad guys.
I could try to envision what type of AI you are thinking of and how would you use it, but I would prefer if you tell me. So, what would you ask your aligned AGI to do and how would it interpret that? And how are you so sure that most alignment researchers would ask it the same things as you?