Posts
Comments
Just looking at the list of "subtle cases of unwholesomeness" makes me not want to adopt the model of wholesomeness in my behaviour. All of these things, except the second one, seem reasonable to me. Not "sometimes", but as a concept of available actions. Model of wholesomeness feels very restrictive and ineffective. I'm not sure I understand why wholesomeness should be implemented when we have other common ideologies of morality that would condemn all of the things on the first list (list of extreme cases) as "bad" (and I think those should be considered bad) without restricting us in a way this system would. The text mentions that sometimes unwholesomeness should be accepted as a "necessary cost", but I'm not sure I even see some of these things as negatives in first place, depending on the context. I think its OK to be harsh and its OK to hurt feelings when situations call for it. It may not only be necessary, but beneficial. As well as gaming a poorly designed system to get ahead of everyone else - it all depends on what the system is, what you do with the gains, and what the public reaction will be.
I understand I may sound a bit cynical here, but this is something I have accepted as part and parcel of society. There are some specific cases of unwholesomeness that I think need to be addressed and removed, and there are other cases where I would personally keep them in place or even add them in where they are missing.
If you can recreate even 1% of his consciousness with this kind of data I would be surprised.
The button isn't showing up for me. Well, it shows up for like a second after I re-load the page but then it's gone. I tried Opera GX browser and Chrome, it happens in both. Is this intended behaviour? I use Windows 7, maybe thats why...
I would argue that the most complex information exchange system in the known Universe will be "hard to emulating". I don't see how it can be any other way. We already understand the neurons well enough to emulate them. This is not nearly enough. You will not be able to do whole brain emulation without understanding of the inner workings of the system.
If we look at 17!Austin and 27!Austin as two different people, then I don't see why 27!Austin would have any obligation to do anything for 17!Austin if 27!Austin doesn't want to do it, just like I wouldn't attend masses just because my friend from 10 years ago who is also dead now wanted me to.
If we look at 17!Austin and 27!Austin as a continuation of the same person, then 27!Austin can do whatever he wants, because everybody has a right to change their mind and perspective, to evolve and to correct mistakes of their past.
If we consider information preservation to be important and valuable, then I would argue that 27!Austin already keeps much more of 17!Austin by simply existing than he could by attending masses. 27!Austin and any future version of Austin is an evolution of 17!Austin, and the best he can do to honor 17!Austin is to just stay alive.
And it keeps giving me photorealistic faces as a component of images where I wasn't even asking for that, meaning that per the terms and conditions I can't share those images publicly.
Could you just blur out the faces? Or is that still not allowed?
For typos there should be an option to just select the error in the text and submit it to the author though the web page. That's what they do on some fanfiction websites. The only downside is that a troll could potentially abuse the system.
I think people who are trying to accurately describe the future that will happen more than 3 years from now are overestimating their predictive abilities. There are so many unknowns that just trying to come up with accurate odds of survival should make your head spin. We have no idea how exactly transformative AI will function, how soon is it coming, what will the future researches do or not do in order to keep it under control (I am talking about specific technological implementations here, not just abstract solutions), whether it will even need something to keep it under control...
Should we be concerned about AI alignment? Absolutely! There are undeniable reasons to be concerned, and to come up with ideas and possible solutions. But predictions like "there is a 99+% chance that AGI will destroy humanity no matter what we do, we're practically doomed" seem like jumping the gun to me. One simply cannot make an accurate estimation of probabilities about such a thing at this time, there are too many unknown variables. It's just guessing at this point.
That Washington Post about Bucha... thats just insane. So many lives lost. And the pro-Russian sources are completely silent on this, which is also telling.
Inb4 rationalists intentionally develop an unaligned AI designed to destroy humanity. Maybe the real x-risks were the friends we made along the way...
Brain is the most complex information exchange system in the known Universe. Whole Brain Emulation is going to be really hard. I would probably go with a different solution. I think myopic AI has potential.
EDIT: It may also be worth considering building an AI with no long-term memory. If you want it to do a thing, you put in some parameters ("build a house that looks like this"), and they are automatically wiped out once the goal is achieved. Since the neural structure in fundamentally static (not sure how to build it, but it should be possible?), the AI cannot rewrite itself to not lose memory. If it doesn't remember things, it probably can't come up with a plan to prevent itself from being reset/turned off, or kill all humans, or build a new AI with no limitations. And then you also reset the whole thing every day just in case.
Could it be possible to build an AI with no long-term memory? Just make it's structure static. If you want it to do a thing, you put in some parameters ("build a house that looks like this"), and they are automatically wiped out once the goal is achieved. Since the neural structure in fundamentally static (not sure how to build it, but it should be possible?), the AI cannot rewrite itself to not lose memory, and it probably can't build a new similar AI either (remember, it's still an early AGI, not a God-like Superintelligence yet). If it doesn't remember things, it probably can't come up with a plan to prevent itself from being reset/turned off, or kill all humans. And then you also reset the whole thing every day just in case.
This approach may not work in the long term (an AI with memory is just too useful not to make), but it might give us more time to come up with other solutions.
This framing feels like a much more motivating strategy, even though it's pretty much identical to what Eliezer is proposing.
NY times article disputed the Russian alternative explanations about how the bodies were moved there. I agree that those are bullshit, and I am not disputing that.
That drone footage seems like direct evidence to me, yes.
Is there any direct evidence linking the Bucha massacre to Russian military? Kremlin's alternative theories being bullshit doesn't mean they did it. They just don't really have a motive, though it could've easily been soldiers acting on their own without much oversight going on. Ukrainian government gave out guns to civilians, so it could've been someone else. I've seen Russian army rations lying near the bodies on some of the photos (EDIT: for the record, the photos come from here, which is far from a reliable source, I cannot verify that these photos are from Bucha, I will edit the comment if I find the original source) - could it be that there people were given rations by Russians, and then they were killed by some locals after being accused of disloyalty to Ukraine?
Until we have more information, we cannot know for sure, and should be cautions of any unverified reports. I'd say as of right now it's 65% probability that Russians did it, and 35% that it was someone else.
Edit: if this report is to be trusted, it was Russians after all.
I am Russian and I can confirm that he most certainly did not call for "killing of as many Ukrainians as possible".
He said that there can be no negotiations with Nazis outside of putting a boot on their neck because it will be seen as weakness, and that you shouldn't try to have "small talk" with them, or shake hands with them. He did say "a task is set and it should be finished". He did not explicitly say anything about killing, let alone "as many as possible", at least not in that clip.
It seems like one literally cannot trust anyone to report information about this war accurately.
I most certainly do not think that we should do nothing right now. I think that important work is being done right now. We want to be prepared for transformative AI when the time comes. We absolutely should be concerned about AI safety. What I am saying is, it's pretty hard to calculate our chances of success at this point in time due to so many unknown about the timeline and the form the future AI will take.
I found this post to be extremely depressing and full of despair. It has made me seriously question what I personally believe about AI safety, whether I should expect the world to end within a century or two, and if I should go full hedonist mode right now.
I've come to the conclusion that it is impossible to make an accurate prediction about an event that's going to happen more than three years from the present, including predictions about humanity's end. I believe that the most important conversation will start when we actually get close to developing early AGIs (and we are not quite there yet), this is when the real safety protocols and regulations will be put in place, and when the rationalist community will have the best chance at making a difference. This is probably when the fate of humanity will be decided, and until then everything is up in the air.
I appreciate Eliezer still deciding to do his best to solve the problem even after losing all hope. I do not think I would be able to do the same (dignity has very little value to me personally).
If I am doomed to fail, I have no motivation to work on the problem. If we are all about to get destroyed by an out-of-control AI, I might just go full hedonist and stop putting work into anything (Fuck dignity and fuck everything). Post like this is severely demotivating, people are interested in solving problems, and nobody is interested in working on "dying with dignity".
I still take issue with the Doctor Rock. The Rock is acceptable if the primary function of the job is to be the Rock (like the bullshit security guard). The doctor's job is not to "reassure her patients and reduce their stress" (she is not a psychotherapist), her job is to actually find those three dangerous cancers among many harmless ones. The existence of such doctor is dangerous because it gives people false confidence that they are being treated for their medical issues by an expert when in reality the doctor is just bullshitting. Even if there are many false positive detections, it is better to double check them then to ignore them.
>And of course, she’s not an actual rock. If there was a giant thing on someone’s nose, she would think ‘oh I had better ensure someone actually examines that.’
Apparently not always. There was a case in which police arrested a man in suspicion of shooting and killing his girlfriend. When the police entered his house and found the body, acted confused and didn't really make sense. The police assumed that he had killed her and arrested him. During the interrogation, he acted in bizarre ways and kept contradicting himself, but the detective continued to pressure him. The police assumed that he was culprit because he acted suspicious and in 99% of the situations like this he would be. But as it turned out, he was acting weird because he had been shot through the brain. He was in a dire need of medical attention and was slowly dying from his injuries but the police didn't even do a basic medical check. In fact, he had visible bullet holes on his nose and face, but they were completely ignored because the police didn't even think he could have been the victim.
The man died 10 years after the a seizure which was a result of his injuries. Had the police checked his health earlier, they would've realized that he was a victim, not a culprit, and it is highly likely could've been saved if he was treated earlier.
More information about the story:
https://medium.com/crimebeat/when-the-suspect-is-a-victim-f4a019da6999
I am not an expert by any means, but here are my thoughts: While I find GPT-3 quite impressive, it's not even close to AGI. All the models you mentioned are still focused on performing specific tasks. This alone will (probably) not be enough to create AGI, even if you try to increase the size of the models even further. I believe AGI is at least decades away, perhaps even a hundred years away. Now, there is a possibility of stuff being developed in secret, which is impossible to account for, but I'd say the probability of these developments being significantly more advanced that the publicly available technologies is pretty low.
I probably wouldn't do it. If I am being compensated for writing the note, it means there is a person that is offering to pay me to write the note. Since this is a weird request, and I cannot be sure of the person's motivation, as a safety precaution I would assume malice. Especially if the "compensation" is large. Like, nobody is their right mind would pay me a million dollars to put a note on the wall that says that I wish my family would die just to prove a point. I would assume malice. This person could be a psycho serial killer who would kill my family in two weeks in order to teach me "not to mess with magic" or something like that. Point is, when a weird person makes a weird request, I believe it's better (safer) not to engage. I'd probably call my family and warn them to be careful too, just in case.
Yes, I realized it in the dream. Since it was a Lucid dream, I was fully aware that I am in a dream and remembered how the taste is supposed to be in reality, so I could compare on the fly.
I know for a fact that I see colors in dreams. When I have a Lucid dream I can experiment with my experiences, and I could confirm that I saw colors. I could also feel taste, cold, touch, hear sounds and sometimes experience pain (I once was stabbed in a dream and it hurt like hell, even for several minutes after I woke up). In fact, I found the amount of details objects had to be surprising - when I looked at a stone wall, it looked like a texture of a real wall. When I touched the wall, it felt like a stone wall. Other senses did not get the details as well - when I tired tasting snow, it was kinda cold-ish and kinda tasted like snow, but not really. When I tasted food, it tasted really weird and not really like I expected.