FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. SEE COPYRIGHT DISCLAIMER.

if we solve the AI safety problem as we’ve talked about and then you Max tag Mark who has been talking about this uh for many years get to sit down with the AGI with the early AGI system on a beach with a drink what kind of what would you ask her what kind of question would you ask what would you talk about something so much smarter than you a really Zinger of a question that’s a good one would you be afraid to ask some questions no see I’m not afraid of the truth I’m very humble I know I’m just a meat pie with all these flaws you know but yeah I I have that we talked a lot about Homo sentience I really already tried that for a long time with myself just so that is what’s really valuable about being alive for me is that I have these meaningful experiences it’s not that I’m have what I’m good at this or good at that or whatever because there’s so much I suck at then so you’re not afraid for the system to show you just how dumb you are no no in fact my son reminds me of that you could find out how dumb you are in terms of physics how little how little we humans understand I’m cool with that I think I think um so I I can’t waffle my way out of this question it’s a fair one it was tough I think given that I’m a really really curious person that’s really the defining part of who I am I’m so curious uh I have some Physics questions I loved I would love to understand I have some questions about Consciousness about the nature of reality or just really really love to understand also I can tell you one for example that I’ve been obsessing about a lot recently so I believe that it’s supposed to Noni is right I suppose there are some information processing systems that are conscious and some that are not suppose you can even make reasonably smart things like gpt4 that are not conscious but you can also make them conscious here’s the question that keeps you make at night is it the case that the unconscious zombie systems that are really intelligent are also really efficient so they’re really inefficient so that when you try to make things more efficient we still naturally be a pressure to do they become conscious I’m kind of hoping that that’s correct and I do you want me to give you a hand away the argument for it you know like in my lab again every time we look at how it how these large language models do something we see that they do them in really dumb ways and you could make it make it better uh if if you uh we have loops in our computer language for a reason the code would get way way longer if you weren’t allowed to use them it’s more efficient to have the loops and in order to have self-reflection whether it’s conscious or not right even an operating system knows things about itself right you need to have loops already and so I think this is I’m waving my hands a lot but I suspect that um the most efficient way of implementing a given level of intelligence has Loops in it the self-reflection it can and will be conscious isn’t that great news yes if it’s true it’s wonderful because then we don’t have to fear the ultimate zombie apocalypse and I think if you look at our brains actually our brains are part zombie and part conscious when I open my eyes I immediately take all these pixels and hit my ref on my retina right and I’m like oh that’s Lex but I have no freaking clue of how I did that computation it’s actually quite complicated right it was only relatively recently we could even do it well with machines right you get a bunch of information processing happening in my retina and then it goes to the lateral nucleus mythalamus into the area V1 V2 V4 and the fusiform face area here that Nancy can wish or an MIT invented and blah blah blah I’d have no freaking clue how that worked right it feels to me subjectively like my conscious module just got a little email it’s like face facial processing fit task complete it’s Lex yeah I’m gonna just go with that right so this fits perfectly with tanoni’s model because this was all one way information processing mainly and uh it turned out for that particular task that’s all you needed and it probably was kind of the most efficient way to do it but there are a lot of other things that we associate with higher intelligence and planning and and so on and so forth where you kind of want to have loops and be able to ruminate and self-reflect and introspect and so on where my hunch is that if you want to fake that with a zombie system that just all goes one way you have to like unroll those loops and it just really really long and it’s much more inefficient so I’m actually hopeful that AI if in the future we have all these various Sublime and interesting machines that do cool things and are aligned with that they will be at least they will also have Consciousness for the kind of these things that we do the great intelligence is also correlated to Great Consciousness or a deep kind of Consciousness yes so that’s a happy thought for me because the zombie of a couple of apocalypse really is my worst nightmare of all it would be like adding insult to injury not only did we get replaced but we freaking replaced ourselves by zombies like how dumb can we be that’s such a beautiful vision and that’s actually a provable one that’s one that we humans can Intuit and prove that those two things are correlated as we start to understand what it means to be intelligent and what it means to be conscious which these systems uh early agi-like systems will help us understand and I just want to say one more thing this is super important most of my colleagues when I started going on in my Consciousness tell me that it’s all and I should stop talking about it I hear a little inner voice from my father and for my mom saying keep talking about it because I think they’re wrong and and and the main way to convince people like that that they’re wrong if they say that Consciousness is just equal to intelligence just ask them what’s wrong with torture or why are You Against torture if it’s just about you know these these particles are moving this way rather than that way and there is no such thing as subjective experience what’s wrong with torture I mean do you have a good comeback to that no it seems like suffering suffering imposed onto other humans is somehow deeply wrong in a way that intelligence doesn’t quite explain but if someone tells me well you know It’s Just an Illusion Consciousness uh whatever you know I would like to invite them the next time they’re having surgery to do it without anesthesia what is anesthesia really doing if you have it you can have it local anesthesia when you’re awake I have that when they fixed my shoulder right it’s super entertaining uh what was that that it did it just removed my subjective experience of pain it didn’t change anything if it was actually happening in my shoulder right so if someone says that’s all and skip the anesthesia as my advice this is incredibly Central it could be fundamental to whatever this thing we have going on here it is fundamental because we’re we what we feel is so fundamental is suffering and joy and pleasure and meaning and that’s all those are all subjective experiences there huh and let’s not those are the elephants in the room that’s what makes life worth living and that’s what can make it horrible if it’s just a bunch of suffering so let’s not make a mistake of saying that that’s all and let’s not make the mistake of uh not instilling the AI systems with that same thing that makes us um special yeah Max uh it’s a huge honor that you will sit down to me the first time uh on the first episode of this podcast it’s a huge honest sit down with me again and talk about this what I think is uh the most important topic the most important problem that we humans have to face and hopefully solve yeah well the honor is all mine and I’m so grateful to Youth for making more people aware of the fact that Humanity has reached the most important fork in the road ever in its history and that’s turn in the correct direction

FOR EDUCATIONAL AND KNOWLEDGE SHARING PURPOSES ONLY. NOT-FOR-PROFIT. SEE COPYRIGHT DISCLAIMER.