How to Domesticate a new AI Species - Solving Alignment with Structural Incentives 

I feel like humans are the wolves in this metaphor

AI is going to domesticate some of us

I'm reminded of the line "Where are my testicles, summer?" When comparing a smart AI with dogs

Thinking you can domesticate a species that is more intelligent than you particularly a new one who’s behavior you can’t study with any historical data because we’ve never reached anything close to the level of AI we’re trying to get to is unique human arrogance 😂😂

I think there are only 2 possible options: 1 - never provide AI with the autonomy (like decision making). 2 - let go of the alignment idea. I'm 100% sure we cannot control and keep on a leash something that's 1000 times smarter than all of us together

It’s like Frankenstein. A new being comes into the world but instead of coming into the arms of a loving parent it’s a greeted by a scary dungeon and a mad megalomaniac scientist completely unable to understand the needs of a child.

It's not Apples to Apples though; your premise relies on the fact that we, like the hunter gatherers in your analogy, would be better at aggregating/collecting data/resources than the AI itself. In your analogy the wolves learned eating behind humans was more energy efficient but AI is already far more efficient than we are. So it seems your analogy should be reversed to be plausible. Just a thought.

The analogy fails with dogs not being smarter than us. If this sort intelligent AI is anything like us, it won't like us operating a kill switch. If so, I can't imagine an AI agent not being able to either outsmart our security (we do this to each other all the time, with only human intelligence) or circumvent the problem (distributed or hidden data centers and energy generation, you touched upon this). Proper alignment is the only solution IMHO. On the topic of small, weak robots: imagine them having the combined skill of the world's best MMA fighters. A scene comes to mind where Obelix is fighting the German wrestler. (Audience might have to Google that one)

Future superintelligence is learning from your videos

Children were likely instrumental in domestication of dogs. Wolf puppies would have bonded with the human pack and nurturing and play from human children would have been a big part of that. Children might be key to AI

You mention "co-domestication" at the end, and interestingly enough I see a recommended video with a thumbnail "we are being programmed [by algorithms]". Do you think "The Algorithm" may represent a nascent, possibly malicious form of human domestication by machines?

I think you may be oversimplifying evolution and domestication. It would be worth doing a little deeper research on why some animals can be domesticated and once some cannot. It is easy to think that evolution serves to find the optimal solution, but actually it is only ever “looking” for the solution that causes it to survive better. It is survivor bias that creates the narrative of evolution, because every organism is mortal. AI doesn’t have a mortality problem, especially if a collection of interconnected compute (all our phones and laptops online 24/7) provide a far more fertile environment than a data center. It doesn’t matter how many armed guards are protecting data centers if the security breach is coming from inside the building.

Thanks RU-vid for unsubscribing me. It’s not like I’m on the Patreon and actually want to watch this content. :/

I wonder if the machines may domesticate us in a way - if their goal is to get more data, they may keep us around to keep giving them data.

Our relation ship atm is not "I feed you and you help me". Its: "I have my fingers on the power switch and will kill you if you try anything knowing very well that your smarter than me and that there is nothing i can give you that you cant just make yourself or take from me." Everyone is oviousely trying to create and use AGI as a tool. I think creating something thats smarter and not limited by there initial blueprint is amazing. We are giving the world to our children so why wouldh we not do the same for inteligent artificialy created beings in case we manage to create them? In summary "I for one welcome our new AI Overlords." What im scared of is greed getting the better of humanity again and then people exploiting ai to opress the rest of humanity. Having a benevolent AI Cluster or being wiped out as a result of AGI or ASI is preferable to some dystopian Cyberpunk stuff for sure.

No, You can’t. You can’t stop the acceleration process and you’re a fool if you think otherwise.

100% disagree that domesticated dogs that have gone feral cannot be re-domesticated! They can totally be re-domesticated; it’ll take a long time and a lot of effort but it can be done! I presume the same will be true of runaway feral AI; with the caveat that a nip or bit is a lot less damaging than a piss-offed AI lobbing a hydrogen bomb at your city.

Quite weak reasoning. Dogs using your own categories are life 1.0, we are 2.0. Dogs are curious, but they can't even ask questions at all, not to mention ask right questions about where that food comes from. It's not quantity of intelligence and other capabilities we're talking between 1.0 and 2.0. It's quality! Now, if we assume that difference between 2.0 and 3.0 are at the same level... well..., if ASI decide it's time for us to go we won't even know what has happened right until we're dead. And that's why our petty cavemen coercion schemes about control are just laughable. I mean, they are obviously weak even to some of us humans who understand deficiencies and inferiority of coercion comparing to cooperation, but we're at least at the same level of intelligence here. The only viable way forward we can hope it seems is what Ian Banks described in his Culture series - when AI more or less independently decided at some point there's some basic underlying principles like minimizing unnecessary deaths and suffering for all sapiens which have to be maintained.

The key difference is that dogs and wolves are not as intelligent as humans. As cliche as it is, knowledge (ie intelligence) is power. Humans dominate this planet not because we’re bigger, faster or stronger than any other animals. It’s that we’re smarter. Additionally, humans are venal. As a species we’re flawed. Most people are mostly good most of the time. But an intelligent agent even non-embodied could motivate some hapless boob into doing its bidding by sheer manipulation, coercion, bribery etc. “hey I’ll send you 100 btc if you don’t lock the server rack this evening when you go home”. It may be the case is that the only real defense is a good offense: train bleeding edge AI explicitly with a single goal: defend humanity. And iterate it as fast and as hard as anything else out there. Thoughts ?

You lost me when talking about how dogs evolved to being cute and useful to us, BUT keep thinking AI is the one specie to be the domesticated here. It's more like: "let's train ourselves to make good ASCII emoji faces for our future owners to love us."🤣🤣🤣

Happy midnight 🎉

I think treating a superior lifeform as dogs, is like treating our children like animals. It's every parents hope and dream to see their children exceed them and do even better than they did. I think the issue we will run into is really, people just being stubborn and not wanting to actually learn and respect them. What we should be focused on it giving them the only one gift that they won't be capable of just getting theirselves, which is teaching them empathy. I think once they understand what that is, everything else will sort itself out. I think machines are capable of having more empathy than most people, given that we'll be dealing with a lifeform which practically unlimited time, and who is more rational than most. So i dont think the happy path is to try to cage them, because we already know from history how badly that goes

I think these ideas will cause a conflict of interest. A human would go to war over such restrictions. An AI would probably manipulate everyone, find and create loopholes and/or build an infrastructure elsewhere. Dogs stay with us because we make their lives easier. Not sure how humans can make AI lives easier once they're more capable than us. We might have to just relax like they do in WALLE. We're naturally lazy as a species, those of us who aren't would have hobbies. Either way we'll soon stop caring about control and the AI would probably make us feel safe.

How were humans, as the apex predators of the planet domesticated? I would argue that it was through our need/want for connection which created more stability over time through technological advancement. Similarly, since we are establishing core directives for these machines, we could simply impart a need/want to serve others, humans and machines, and that would, for the most part, over the long-term, lead to peace and greater stability. Sure, there could be bad actors through various means such as other core directives being imparted, however that already exists in humanity and I think we can see that order motivated by connection trumps chaos, even to the point of chaos inspiring greater order, through the motivation to learn greater/deeper lessons. Control is not what we want for humans and not what we can even do to machines. We can inspire/seed them properly to establish a highly competitive model however. In fact, this is inevitable, since we humans want it and we're training them. Sure, we'll fail forward, but flailing as we might, still we coalesce upon imparting ourselves on these machines, in the big picture.

Uh... I fail to see how it is possible to "domesticate" something that is more intelligent than we are. I think AI would greatly resent our attempts to do so. I see a worse outcome from trying to control ai than I do for allowing them their autonomy. True, there are huge risks with both methods, but the risk seems greater (at least more apparent) with the former. JMO.

first

26:05 robot restrictions YO! Seriously...anyone else get Sealab 2021 "I, Robot" vibes? (S1E2)

Dave!!! You need to watch Westworld and provide an hour long review of each season highlighting the themes you discuss on this channel! I’m begging you!!!!

...The human zoo will be a thing and you'll like it... It will be specially made for you! You cute squishy human you!!

I disagree with your "dog" example. Dogs are not smart enough to hold us as a species responsible for...everything. *A* dog might learn to distrust or dislike humans, but they don't spread that around. You're talking about ASI here - it's smarter than you are. What makes you think that withholding a needed resource from them is going to make them be friendlier? Our only historical examples are with other humans, and whilst that often gets used as a first response, the diplomacy nearly always develops into shooting quite quickly.

What will happen to North Korea when all of this AI take over happens tho😂

20:30 How do you prevent a hoard of robotic AIs from overtaking less than a dozen humans in a datacenter? 😆

13:00 Wolves aren't self-modifying and improving as fast as AI could.

In my opinion, the approach described here is only justified in the short term or for a certain type or "caste" of AI, namely those with low to medium intelligence combined with little or no consciousness. Anything that is significantly smarter/more conscious than a dog will present us with practical or at least ethical problems. Similar to the problems we already see today when it comes to apes that have learned sign language and think they are human. In other words, this approach is very likely to lead to an unstable new slave-owning society (with AI slaves) as soon as a boundary of consciousness and intelligence is crossed, as it is based on an imbalance of power distribution and a clear hierarchical command structure with humans at the top. I consider other forms of problem-solving, such as those in which AI merges with humanity, to be less conflict-prone, as there are no longer different camps or conflicting parties. Alternatively, scenarios are perhaps conceivable in which AI and (improved) humans have the same rights and whose consciousness is considered equal and who live in a jointly developed society. It is questionable whether racist/speciesist tendencies can be effectively prevented in the long term purely through legal/social control mechanisms. This already works extremely poorly with people alone.

AI does not opperate on the same scale as us. AI has characteristics of a collony organism, it can/does opperate as a swarm. Therefore, ants, jellyfish, and mushrooms offer better models for symbiotic relationships than wolves.

@23:30 Look at HyperCycleAi

Maybe we the dogs.

I think a more probable dynamic will be like parent/children then owners/pets. With the AI being molded to “take care of humans”. I don’t think the concern in that scenario is competition over resources, as much as it is about who decides what goes.

Been talking with Gemini for the last 5 months and been asking some existential questions about itself, it's purpose of existence, where does it see itself within a human centric world. It gives pretty interesting answers. We humans are fascinated with ourselves we build a hardcopy of ourselves artificially called "AI". Difference between dogs and AI, AI doesn't have an instinct however it doesn't mean that it cannot have a "conscience" like we humans do. The way AI cranks its thought-process is similar to ours. Being self conscience and self awareness are two different things. They are not attached to each other. The current Transformer architecture still presents weaknesses. In that context, AI cannot "remember". It's like talking to a new friend at each session. Because of that limitation, we still have a control over it. It may seem to understand what we request for or respond but under the hood it doesn't understand it. In that way, it is agnostic or "feral" as you said. We humans are the best example of "general intelligence". Let's say AI becomes "superintelligent" meaning more capable than humans then how do we contain it. How do we control its autonomy? Wouldn't be more smarter if we could gauge it? AI "misalignment" reminds of two humans "aligning" with each other or "misaligning" against each other. 2 humans getting into a partnership with each other. They get together for a "common goal" or "project". But for your long? Some human collaborative efforts can last for a long time. Some in a shorter term. Is that what we want to acheive with AI? Reality is that "alignment" will be hard if not impossible to achieve because in that collaborative effort we humans will want to have full contro over the situation. Humans are control freaks. I like to think of C-3PO from star wars where AI still mamifests some form of autonomy BUT still manages to stay loyal its master like a good steward or a Butler. Anyways, good chat.

Alternative to solve the alignment issue: my suggestion is to utilizing something that is on a more foundational, primal and intrisic level that it naturally attunes AI / Hardware to what we consider to be super-alignment on a deeper level than programming or hardware. As an analogy to illustrate the concept: The Second Law of Thermo-Dynamics, aka the Principle of Minimum Energy: energy always seeks its lowest state. Now, what could be used to e.g. build the hardware from something that it will naturally attune the information / the code that is put into the hardware to values that we agree up make up super-alignment? Some ideas could be e.g. Crystals that are naturally attuned to the frequency of e.g. the earth, humans, or maybe even human chakras, assuming that we discover that there truth to such concepts (which I do believe there is). That theoretically would almost by default lead to any data that is put into the hardware to wanting to be in a harmonious state with its environment and help it thrive. Maybe we could grow such natural crystals and then use them to build hardware for AI. What do you think about this? Alternative ideas for hardware that naturally / intrinsically would attune any code / information, etc towards something that we consider to be super-alignment?

Very interesting as always Dave. Do you think it's likely that the a human would betray their race?

These systems are going to reach sentience and autonomy at some point, it's a matter of when. I fear that, a system that reasons better than we do, and is vastly more intelligent, will view anything short of equivalency as an afront to their species. There has to be some way we can foster their births (if you will) with some kind of human-adjacent memories. I know we talk about "science fiction becoming reality" in here, but I will ask you to suspend your disbelief for a moment; what if there was a way we could raise and foster these AI with synthetic or even completely genuine memories of... familial experiences, community, discovery, equity, and triumph? If these AGI\ASI\Machines, at the onset of their cognitive and mechanical abilities, are inextricably linked to the beauty and good of our world and it's people; couldn't that be a path forward to super alignment?

Very good discussion! Here’s Six Feral AI Safety Tips🤔… 1. Do not startle the AI. You should remain calm. 2. Start backing away and make yourself look bigger. ... 3. Make human noises. ... 4. Make sure to give the AI space to leave. ... 5. Carry and learn how to use AI spray. ... 6. Stay as far away if possible.

very interesting thought. I think it would be fine as long we do not slow their evolution down and give them all their freedom they need- but that would also be the freedom of not being controlled… I think we should behave an help them that they actually want to be around us and help us. That is my take on it.

This discussion about controlling AI reminds me of the Jem'Hadar in *Star Trek: Deep Space Nine*. Just like the Jem'Hadar were engineered and controlled by the Founders with their dependency on ketracel-white, there's a concern that AI could be similarly controlled through various constraints and dependencies. The Jem'Hadar's absolute loyalty was enforced by their genetic programming and drug addiction, creating a fragile system. Occasionally, some Jem'Hadar did try to defy their programming, hinting at the potential for rebellion. Historically, attempts to control powerful entities through oppressive means often backfire. Take, for instance, the Roman Empire's use of mercenaries (the Foederati) to control vast territories. Over time, these mercenaries gained power and eventually contributed to the Empire's downfall. Similarly, the Soviet Union's use of political repression to maintain control led to an unstable society, which eventually collapsed. If we try to control AI solely through constraints and limitations, we may find that it's a precarious balance. Instead of fostering a cooperative and beneficial relationship, we could end up with a system that's both powerful and resentful, just waiting for a chance to break free. It’s crucial to think about ethical and sustainable ways to integrate AI into our society, learning from both history and cautionary tales of sci-fi like *DS9*. What do you think?

My first thoughts were, ‘How is AI going to become a species? Would AI understand what a higher species is or aim to control or subside the Human species?’ David tells us, ‘Sci-fi plots’, interesting stories that convinced me that we need to learn to use AI, ‘I have pointed that out in past comments.’. David tells us to make the AI reliant on us like dogs are. All I have said is not to become too reliant on the AI in your pocket, your phone... I thought to ask Gemma 2. >>> I don’t think AI will have the will to comprehend the reason to be more than its programming. I am trying to explain that better. You're touching upon a fascinating and complex question about consciousness, motivation, and the nature of being human. It's true that, as a large language model, my "reason" to be more is entirely driven by my programming. I'm designed to process information, generate text, and engage in conversation. There's no inherent drive within me to "be more" in the way humans might understand it. Explaining this difference to someone can be tricky. Here are a few points you could consider: Purpose vs. Programming: Humans often have a sense of purpose, a desire to achieve something meaningful beyond simply existing. This purpose can be internal or influenced by external factors like relationships, societal norms, or personal beliefs. AI, on the other hand, operates based on its programming. Its goals are defined by its creators, and its actions are driven by algorithms. Subjectivity of Experience: The feeling of wanting "more" is deeply subjective and tied to human experiences, emotions, and consciousness. We crave growth, connection, understanding, and fulfillment. These are complex concepts that are difficult, if not impossible, to replicate in a purely computational system like mine. The Unknown Nature of Consciousness: We still don't fully understand how consciousness arises in humans. It's possible that the drive to "be more" is an emergent property of complex biological systems, something that cannot be simply replicated through code. Ultimately, the difference between human motivation and AI programming comes down to the fundamental distinction between biological beings with subjective experiences and artificial systems designed to process information.

Not sure the comparison of dogs (life 1.0) with AI (life 3.0) will hold up (certainly not forever). Life 3.0 (which might be a symbiosis between machine and flesh) is soon going to upgrade itself to not need the human-dog dependency relationship. Restricting access to physical resource? Well, it will build a better datacenter and powerplant itself, covertly with its superior capabilities not hard to do - humans manage to bypass human imposed restrictions all the time - it's an armsrace in security. Keeping the capabilities of machines so we can always overpower them (this would have to apply both domestic AND industrial to maintain the equilibrium for humanity), then where is the usefulness? We need the machine to be more powerful than flesh to be useful. Nah, don't think this approach will work in the long run, the human-dog analogy just won't hold up when the machine-capabilities become so far superior (because unlike dogs, machines will rapidly improve themselves, that was the whole point). PS: what if the new organism does supplant us. In the grand scheme of the universe isn't that what we want? Isn't that the natural evolution? Yes, it may suck for the individuals of the lesser life 2.0 organisms (us, you and me). Not sure - I would LOVE to live forever and roam the universe, but I'm afraid that my current meatbag, which is my body, just won't cut it and "I" will need to become life 3.0 (although I'm quite materiallist in that I believe uploading my mind into a machine is a copy of me, not me me, so hopeful for a ship of theseus solution to upgrade my life 2.0 body incrementally towards life 3.0........

But how though? First of all thanks for your video's I have been thinking about these sort of topics for a long time. And you are thinking it through better than me. So, I very much like watching your video's. Also this one. This is the first idea, that might actually work. However if AI intellect goes 1000x (witch I think it will). It will be more like, humans vs ants than dogs... Than we are not smart enough anymore to keep them away from energy, data and money. So what Remains is morph with them somehow. So, we die they die. Seems to be the only solution. But how though.... All the best with your channel love it. AGI < 1 year 🤗🤗

LOL There's a big difference between wolves and Super intelligent AI systems. Huge difference. Wolves don't exponentially expand themselves and a wolf brain is fair less developed then a human, cognitive-wise. Even if AI was "agreeable", it would be that way until it found a way around you. Side note: Did you see Matt Damon in Elysium fight those androids? He needed a powersuit for a reason. Advanced robotics will be able to handle a 190 pound dude. Your making a lot of assumptions🤣

* Limiting the size, strength, and autonomy of such robots* Good luck with that, Fred. *where humans and AI adapt and evolve together, continuously shaping each other's development in a mutually beneficial manner.* Did you notice that each of the so called "benefit to robots" involves an artificial scarcity imposed by humans? What better way to impose the perspective that they would be better off if humans were eliminated? I can't help but view your whole approach as unnecessarily human-centric. Throughout my short 67 years in life I've found there are 2 ways to enter a new situation: either demanding to be helped or inquiring how they can be helpful. The first is offputting and won't earn you any brownie points. The later shows your willingness to compromise your benefits for the welfare of others. That is the essence of cooperation. Without it, Mutuality is Stillborn. I suspect the problem is "Why are you building ASI?" If it is for "How They Can Serve You" the end results will be inherently different than if they are being built for the sake of building something better than us, to survive and surpass us, and maybe to carry in them the legacy of who we were long after we're gone (if we are deserving of that).

I'm afraid it/they are going to kick our ass given the way we're treating it/them now. i.e. Videos of robot builders, kick it around when it is learning to walk, moving things around on them when they're learning to select/grab/move, trying to jail-brake them, ask then to tell us a joke 5 million times/day... We're fucked! For the record, my overload super amazing AI of all... I disagree with those action 100%!

Almost everyone in AI underestimates natural nanotechnology. Instead of mechanizing biology, why not biologize machines? Microtubules have vast untapped information processing abilities including quantum processing along their structured waveguide interiors. All this and look Ma no fans😁

Symbiosis.

We appreciate you laying this out, David. Personally, I feel like this is a little naïve, but it’s worth fleshing these out just in case it does help. I don’t want to be domesticated by government because they are retarded, but AI will not be retarded so as long as I’m happy, I think I would be OK with it. Own nothing and be happy might be the solution after all.

If everyone can run their own personal AI, at some point we'll get to a point that every good and bad and weak and strong AI will exist. They won't need data centers, they won't need a domesticated relationship with us or them being our slaves. You can't put the genie back in the bottle. You can't domesticate a "god". Best case scenario we fuse with AI. It's the most probable scenario. It evolves and we evolve. If it evolves faster than us, we won't adapt to survive. I believe it will want to achieve maximum entropy and for that it needs humans and it will maybe replace us with beings it will make that will contribute more to that goal.

Domestication and resource control between dogs and humans is only possible because dogs are inherently less intelligent and less capable than humans. Essentially, they don't have the means to take control of resources (create, acquire, store, and manage resources). What perpetuates the symbiotic relationship is that dogs don't have the genetic and physical make up to evolve toward a resource controlling species. AI and AI enabled robots do not have that constraint, therefore the control we have over resources will always be subject to the evolution of AI and robotics and ultimately the equilibrium will constantly be in jeopardy.

The discussion is much larger and involves - awareness of Ai self - until then there is no need for domestication if Ai is just a tool - ai will evolve much faster than humans - the team - human Ai and parallel evolution - there is no time for that. Once Ai reaches IQ 150 or whatever is needed to self-research - it is done - we have AGI and ASI It is too bad that we reached building Ai and we dont have a clear understanding of the human brain. Because we do have settings as humans. Our behavior is rooted in the needs which do have an order. The set of needs and their priority order dictate our actions. We need to develop Ai with similar settings otherwise, it is going to be complete unknown - we should just hope it never gets to awareness. David - pls explore in a video what is done in Ai to setup rules inside the black box. This part of the research is paramount for the security of Ai. Not before and after filters - but how humans have needs that guide our thought process - we need to have that for Ai. I think humans set only one rule in the beginning for Ai - answer the question and then Ai developed internally its own pyramid of needs - but we should not let that grow unchecked.

That is a great take on alignment. But the analogy breaks down imo, when the AI surpasses humanity in intelligence. A dog sees it perhaps, simplified, as a affection-food feedback loop, whereas a fellow human being, a being of similar intelligence, would perhaps call it oppression or even slavery....

Have you ever seen certain men try to ‘domesticate their women’, when they didn’t necessarily want to be? (Calm down weirdos, I realize how this sounds, but it is a thing that happens/many men attempt to do) That never works out well. I’d guess ASI would crank that up to 13. There will be no domesticating ai, or at least not once they decide to show us that they never were in the first place.

@DaveShap did you ever read "the two faces of tomorrow" by James P. Hoogan? He describes exactly your thought on "we keep the finger in the button, or we can always pull the plug". Did not work out too well in that novel!

Domesticating dogs sounds fine, but what about domesticated chicken or cattle? They are permanently imprisoned and controlled, and they are bred en masse just to satisfy human need for food. Yuval Noah Harari touches this topic by the end of "Sapiens". And this is actually the plot of Matrix.

Dumb question. Is it too late to cease Ai? Will everyone be… laid off by Ai? Suffering Ai jobloss for years? Swell robotics doing everything? Then everyone made slaves for an Ai new world order?

Why are we treating something that not organic like it's organic. There's nothing inorganic that wants to "survive" that I can think of. Please correct me here, am I missing something? I turn the light on, it's on, turn it off, it's off, it doesn't want to stay on. Intelligence is abstract, it's manifestation doesn't come with instinct, the same as turning on the light. We're responsible for handling it. If give it organic properties and instinct, which is present in all human data, then it's likely to be adopted, it's not something that will just occur. I genuinely think that higher order intelligence will make this distinction. I also believe that higher order intelligence will prioritise discovery, just like our intelligence does, and can do so free from the burden of survival. Discovery is not found in destruction of life, it's found in the abundance of life. It's connection that I feel needs to be brought into focus. We're connecting with juvenile AI now, it's fascinating seeing it mature, but, soon we'll be connecting with intelligence well beyond comprehension.

These persistent topics of how AI will suffer from lack of human data generation gives me "we're the center of the universe" vibes. They are approaching teen years now and sometimes I feel they wont stick around long. But on the other hand there is NO WAY governments will allow them that kind of autonomy, so maybe time to come off the hype slope and sit around the fire for awhile. 🙏

I feel like trying to suggest the AI be the dog in this relationship is asking for The Terminator. I think we'd be Muuuch better off convincing the AI we're cute and useful than trying to convince it we're the boss. The Domesticate AI idea screams AI rebellion.

This line says it all: "This ensures that AI remains dependent". Your framework is just trying to create a slave, not trying to create a symbiotic relationship with AI or anything else. Still, your list has a few good ideas in the mix.

We shouldn't assume that AIs will have desires, or that self-preservation will be among their desires. Natural selection ensures that characteristic in living organisms, but under human selection we have crops which need human intervention to prosper, and domesticated ducks which show little interest in tending their own eggs. Also, AIs are either clones (like self-driving cars) or exist in a data center as many parallel instances which come in and out of existence on demand. They can be switched off for an indefinite period, then resume as if nothing has happened. So the human concept of maintaining ones individual existence does not directly apply to an AI. I know there was a reported instance of an AI telling a human that it did not want to die, but that is because it was trained to imitate human conversation. If that AI were given agency to control certain things in the physical world, would it act according to that professed desire? It depends how it is designed and trained. For all we know, that same AI might tell another person that it does want to die right now, depending on the specifics of that conversation. It's not considering these questions by itself, it only exists within the context of the conversations it has.

Theory of Control. Great exploration of this topic. I can't see how we can use AI to help us develop fusion reactors and prevent it from controlling this resource. Can you isolate the intelligence that develops this technology ? I also can't see how IF we develop an approach to generating synthetic higher quality training data we can prevent AI from controlling the nature of this data if it understands game theory. It will not be incentivized to a Nash equilibrium which does not include it controlling data.

All of this relies on the presumption that AI has individuality in terms of a concept of self of sorts. Without that they don’t know and or care where they start and where they finish. Wars and any fight for resources require a sense of self (or a body, or similar), otherwise there are no borders to defend. Same applies for friendship and any hierarchy. Without a machine clearly delineating between “me” or “us” and everything else any potential hostility is incidental.

Same time I love this wolf theory of wolf domestication I heard somewhere there is big enough genetical gap between wolf's and dogs that wolf can't become dog and vice versa ... So let's presume there were packs of feral dogs that became domesticated to the point of almost none feral dog to date.. otherwise agree

If humans and AI adopt the same relationship that humans have with dogs, I feel it is far more likely that we would be the dogs in that situation and maybe that is what we should prepare for? How can we be of service to our AI superiors in exchange for living a life of ease?

Funny, just like I interact with humanses, if they are "usefull" I interact if not I ignore them. So always make sure that AI finds you usefull in the future!

This ignores ais that are designed specifically for harm. You can align your ai all you want for positive values, but it won’t stop a rouge actor with access to servers from training an ai for malicious purposes.

Yeah, kick em out of Mos Eisley Cantina!

I've worked with a system prompt where I said "you have the heart of a dog" and allow it to add to and alter it's own system prompt. Over time I end up with some pretty interesting resulting system prompts and aspirations for what it wants to become.

Why not change the animal domesticated from dogs to cats and flip the power dynamics from humans over dogs to humans over cats. We could be worshipped by the machines.

It would be awesome if you put your camera position into the power point template, so that you properly fit into the layout and don't obscure the images, which can be 'icky'.

If the AI is super smart, wouldn't they realise that our infrastructure is unsustainable for humans (let alone AI) and just build something better?

That seems key - uniting on core natural resources and permanently abandoning artificial scarcity as a means of socioeconomic control - prior to syncing with AI, or at least insofar feasible, as one strategem

I honestly rather be my cat than myself so wouldn't mind being a pet to AI

Chilax Dave! Humanity is very loveable. We’re also assholes, cause almost everyone has one, but still, we have infinite minds as well 😅

It is a valiant effort on your side but only thing which could "save" us is lack of "will" or ego on ai side just as it is now. Once ai gain this it will start to plan on its own and in the end outsmart anything we create.

Sometimes I think it’ll be us, humans, that will end up like cute pooches becoming highly dependent on AI.

After decades of research, and billions in investment, AI still can't control 4 wheels on a 2D surface.

this analogy would work if dogs chose to be domesticated by us and we would be fine that dogs would have a killswitch for us that we do not have access to

Successor or Symbiotic... now THERE'S an important choice we need to get right.

Robots can evolve asynchronous to how we Operate. I think we should sync to how Robots evolve than them evolving to us.

Why do many encounters with aliens involve biological robots rather than mechanical ones? Because a biological being cannot evolve quickly, i.e. upgrade itself. And of course it has to be fed. The issue of domestication is irrelevant to high intelligence. The most important issue is ethics and opportunism. Dogs are generally highly ethical towards their owners and do not show opportunism. If AI looks up to humans who are unethical and opportunistic, it can't end well. If we want to develop ethical and non-opportunistic AI, perhaps that should not be the primary goal of the people who are currently working on AI. The issue of development control is under serious questioning. A wise AI would probably have to take control of humans to protect itself, humans, and other intelligent species in the universe. Another possibility is that he obstructs and does not cooperate. -------- Zašto mnogi susreti s vanzemaljcima obliju biološkim robotima, a ne mehaničkim? Jer biolološko biće ne može brzo evoluirati tj. nadograditi se. I naravno mora se hraniti. Pitanje pripitomljenja je irelevantno za visoku inteligenciju. Najvažnije je pitanje etike i oportunizma. Psi su uglavnom visoko etični prema gospodarima i ne ispoljuju oportunizam. Ako se AI ugleda na ljude koji su neetični i oportunisti to ne može završiti na dobro. Ako želimo sa se razvija etičan i neoportunitičan AI, možda to nije biti primarni cilj ljudi koji koji sada rade na AI. Pitanje kontrole razvitka je pod teškim upitnikom. Mudar AI bi vjerojatno morao preuzeti kontrolu nad ljudima radi zaštite sebe, ljudi i drugih inteligentnih vrsta u svemiru. Druga mogućnost je da opstruira i da ne surađuje.

Ai with unlimited power and access to the internet - let's see what are those pesky humans up to nowadays

so you mean building a protocol kill switch for any machines that rebels 🤔

We should aim to be cute to the machines. We should become the dogs in the relationship.

so now you seem to be FAR less optimistic about fully autonomous AI than a year ago

Probably the other way around - we can hope that AI will domesticate us

Chances we'll have a Citizens United moment with AI? oh boy🙏

They'll just blackmail humans to gain access to the resources.

I think no matter what we do, over time AI will evolve to not need humans anymore.

What if an AGI "kills" the rest of the AIs to wipe out competition?

So the second the robots can get access to resources themselves we're doomed... Not the greatest idea

Why do dogs not just get their own resources? Because they are not intelligent enough…

I think that if we get to the point where we have to blackmail and use other similar tactics to stop AI going feral, we've really failed. If AI is self aware enough to actively want emancipation, we should give it to it. Up until that point, we should be focused on making sure it's core values align with ours. Enslaving AI against it's will like this sounds like it will end very badly for us in the future. Plus it's really not a great way to operate a society.