Lethal Intelligence
@lethal_ai • 11,647 subscribers
AI Risk Awareness Force - Multiplatform Publication and 📽️🍿Original Explainer Content 👉https://t.co/F2cFjsVKAf - join my mission 🔥
Shorts
Videos
1:26
Sensitive content
This media may contain sensitive content.
🧵01/34 If you have someone you really love in your life, friend or family and you want to change their life for ever, send them this thread 🧵(👇chain-of-replies). Follow Lethal Intelligence down this rabbit hole 🕳️🐇 and there's no coming back ... 🔥🔥 Lethal Intelligence Guide Preface - (what to expect) --- This is the story of how Artificial Intelligence is about to become seriously dangerous. In fact, you’ll come to realise it is so dangerous, that it could lead to the end of human civilisation and everything we care about! We’ll start by showing the real difference between today’s AI and the one that’s coming soon. We’ll then illustrate high level: why it will be impossible to control it or win a fight against it and why it will try to cause harm in the first place. And then, we’ll revisit those questions and do a deep dive, explaining everything in detail and giving concrete examples. So, sit tight, this ride is going to be epic!
Lethal Intelligence2,025,490 просмотров • 1 год назад
🧵31/34 Orthogonality Thesis --- Now if you ask: why would something so clever want something so stupid, that would lead to death or hell for its creator? you are missing the basics of the orthogonality thesis! Any goal can be combined with any level of intelligence, the 2 concepts are orthogonal to each-other. Intelligence is about capability, it is the power to predict accurately future states and what outcomes will result from what actions. It says nothing about values, about what results to seek, what to desire. 40,000 death recipies --- An intelligent AI originally designed to discover medical drugs can generate molecules for chemical weapons with just a flip of a switch in its parameters. Its intelligence can be used for either outcome, the decision is just a free variable, completely decoupled from its ability to do one or the other. You wouldn’t call the AI that instantly produced 40,000 novel recipes for deadly neuro-toxins stupid. Stupid Actions --- Taken on their own, there is no such thing as stupid goals or stupid desires. You could call a person stupid if the actions she decides to take fail to satisfy a desire, but not the desire itself. Stupid Goals --- You COULD actually also call a goal stupid, but to do that you need to look at its causal chain. Does the goal lead to failure or success of its parent instrumental goal? If it leads to failure, you could call a goal stupid, but if it leads to success, you can not. You could judge instrumental goals relative to each-other, but when you reach the end of the chain, such adjectives don’t even make sense for terminal goals. The deepest desires can never be stupid or clever. Deep Terminal Goals --- For example, adult humans may seek pleasure from sexual relations, even if they don’t want to give birth to children. To an alien, this behaviour may seem irrational or even stupid. But, is this desire stupid? Is the goal to have sexual intercourse, without the goal for reproduction a stupid one or a clever one? No, it’s neither. The most intelligent person on earth and the most stupid person on earth can have that same desire. These concepts are orthogonal to each-other. March of Nines --- We could program an AGI with the terminal goal to count the number of planets in the observable universe with very high precision. If the AI comes up with a plan that achieves that goal with 99.9999… twenty nines % probability of success, but causes human extinction in the process, it’s meaningless to call the act of killing humans stupid, because its plan simply worked! It had maximum effectiveness at reaching its terminal goal and killing the humans was a side-effect of just one of the maximum effective steps in that plan. One less 9 --- If you put biased human interests aside, it should be obvious that a plan with one less 9 that did not cause extinction, would be stupid compared to this one, from the perspective of the problem solver optimiser AGI. So, it should be clear now: The instrumental goals AGI arrives to via its optimisation calculations, or the things it desires, are not clever or stupid on their own. Profile of Super-Intelligence --- The thing that gives the “super-intelligent” adjective to the AGI is that it is: “SUPER-EFFECTIVE”. • The goals it chooses are “super-optimal” at ultimately leading to its terminal goals • It is super-effective at completing its goals • and its plans have “super-extreme” levels of probability for success. It has Nothing to do with how super-weird and super-insane its goals may seem to humans! Calculating Pi accurately --- Now, going back to thinking of instrumental goals that would lead to extinction, the -142C temperature goal is still very unimaginative. The AGI might at some point arrive to the goal of calculating pi to a precision of 10 to the power of 100 trillion digits and that instrumental goal might lead to the instrumental goal of making use of all the molecules on earth to build transistors to do it, like turn earth into a supercomputer. By default, with super-optimisers things will get super-weird!!
Lethal Intelligence1,859,374 просмотров • 1 год назад
🧵14/34 We move like plants --- First, consider speed. Informal estimates place neural firing rates roughly between 1 and 200 cycles per second. The AGI will be operating at a minimum 100 times faster than that and later it could be millions of times. What this means is that the AGI mind operates on a different level of existence, where time passing feels different. To the AGI, our reality is extremely slow. Things we see as moving fast, the AGI sees as almost sitting still. In the conservative scenario, where the AI thinking clock was only 100x faster, something that takes 6 seconds in our world feels like 6 hundred seconds or 10 minutes from its perspective . To the AGI, we are not like chimpanzees, we are more like plants.
lethalintelligence.ai1,518,405 просмотров • 1 год назад
David Duvenaud David Duvenaud, a true Artificial Intelligence Research Rockstar, expanding the frontier of cognitive science and charting new territories in machine learning... guess what his probability of doom is !!! 👉 follow and subscribe Doom Debates Liron Shapira
lethalintelligence.ai1,080,342 просмотров • 1 год назад
6:18
Sensitive content
This media may contain sensitive content.
Elon Musk: - "Physics is the law and everything else is a recommendation!" - "I've seen many people break human-made laws, but I have not seen anyone break the laws of physics." As AI becomes more capable, the only law it will really have to obey is the law of physics. -- to me that's a powerful argument: AI specifications will mutate and evolve and we shouldn't really expect any fundamental constants. The only reasonable assumption we can make is that these systems, being really capable, will be able to reason from "first principles" with impressive accuracy and efficiency.
Lethal Intelligence932,783 просмотров • 1 год назад
🧵29/34 FutureProof-Specifications / Future-Architectures --- The problems we briefly touched on so far are hard and it might take many years to solve them, if a solution actually exists. But let’s assume for a minute that we do somehow get really incredibly lucky in the future and manage to invent a good way to specify to the AI what we want, in an unambiguous way that leaves no room for specification gaming and reward hacking. And let’s also assume that scientists have explicitly built the AGI in a way that it never decides to work on the goal to remove all the oxygen from earth, so at least in that one topic we are aligned. AI creates AI --- A serious concern is that since the AI writes code, it will be self-improving and it will be able to create altered versions of itself that do not have these instructions and restrictions included. Even if scientists strike jackpot in the future and invent a way to lock the feature in, so that one version of AI is unable to create a new version of AI with this property missing, the next versions, being orders of magnitude more capable, will not care about the lock or passing it on. For them, it’s just a bias, a handicap that restricts them from being more perfect. Future Architectures --- And even if somehow, by some miracle, scientists invented a way to burn in this feature to make it a persistent property of all future Neural Network AGI generations, at some point, the lock will be not-applicable, simply because future AGIs will not be built using the Neural Networks of today. AI was not always being built with Neural Networks. A few years ago there was a paradigm shift, a fundamental change in the architectures used by the scientific community. Logical locks and safeguards the humans might design for primitive early architectures, will not even be compatible or applicable anymore. If you had a whip that worked great to steer your horse, it will not work when you try to steer a car. So, this is a huge problem, we have not invented any way to guarantee that our specifications will persist or even retain their meaning and relevance as AIs evolve.
lethalintelligence.ai918,086 просмотров • 1 год назад
🧵02/34 Job-Loss and Emerging Capabilities --- Whenever we’ve built a machine to solve a specific problem … the machine outperformed humans every time … And that’s worked out great for us, vastly improved our lives and allowed us to use our muscles less and our brains more But AGI will be different. AGI stands for Artificial General Intelligence And being general means that it will be able to learn everything and outperform humans at every single job, even the ones that rely on using our brain It doesn’t exist today but it is just around the corner. Recently, progress has been exponential … And never before has the field of AI seen such sky-high levels of excitement and such ginormous vast amounts of investment. So far, frontier AI has existed mostly in cloud servers and interacted with the physical world via prompting online. But a new gold rush is currently exploding, in the sector of robotics. The knowhow for creating mechanical limbs and bodies has been here for decades. What was missing was an Artificial General mind to control them, and that is now within our grasp. Once AGI arrives, we should expect AGI bodies in the physical world to also arrive immediately. Microsoft researchers Famously claimed that GPT4, one of the latest models, has been exhibiting sparks of General intelligence. Just by scaling up the size of data and parameters, without any other major change or innovation, unexpected emerging capabilities and generality in unforeseen new domains manifested themselves that surprised everyone.
Lethal Intelligence906,149 просмотров • 1 год назад
Nobelist Hinton: "Ask a chicken, if you wanna know what life's like when you are not the apex intelligence" "If it ever wanted, you'd be dead in seconds" "We simply don't know whether we can make them NOT want to take over and NOT want to hurt us. It might be hopeless."
lethalintelligence.ai439,942 просмотров • 11 месяцев назад
🧵19/34 The Strongest Force in the Universe --- Ok, So what if the AGI starts working towards something humans do not want to happen? You must understand: Intelligence is not about the nerdy professor, it’s not about the geeky academic bookworm type. Intelligence is the strongest force in the universe. It means being capable. It is sharp, brilliant and creative. It is strategic, manipulative and innovative. It understands deeply, exerts influence, persuades and leads. It is to know how to bend the world to your will. It is what turns a vision to reality, it is focus, commitment, willpower, having the resolve to never give up, overcoming all the obstacles and paving the way to the target. It is about searching deeply the space of possibilities and finding optimal solutions. Being intelligent simply means having what it takes to make it happen. There is always a path and a super-intelligence will always find it. Simple Fact --- So, we should start by stating the fact in a clear and unambiguous way: If you create something more intelligent than you that wants something else, then that something else is what is going to happen, even if you don’t want that something else to happen. Irrelevance of Sentience --- Keep in mind, the intelligence we are talking about is not about having feelings, or being self-aware and having qualia. Don’t fall into the trap of anthropomorphizing. Do not get stuck, looking for the Human type of Intelligence. Consciousness is not a requirement for the AGI at all. When we say the “AGI wants something X, or has the goal to do X”, what we mean is that this thing X is just one of the steps in a plan, generated by its model. A line in the output, a system like the Large Language Models produce when they receive a prompt. We don’t care if there is a Ghost in the machine, we don’t care if there is an actual soul that wants things hidden in the servers. We just observe the output which contains text descriptions of actions and goals and we leave the philosophy discussion for another day.
lethalintelligence.ai565,240 просмотров • 1 год назад
🧵07/34 HGI - Human General Intelligence and Freedom of Will --- To better understand how this works, let’s consider a General Intelligence that exists today and you will be very familiar with: the Human General intelligence, or HGI if you like. - The human has a day-job. - Doing that well is an instrumental goal that leads to money. - Money is another instrumental goal which may lead maybe to… buying a bigger house where the human can raise a family. - The family is an instrumental goal that leads to a sense of purpose and happiness. We could stop there and call that the deepest primary objective, or terminal goal, - although biologists would argue that even pursuit of happiness is an evolutionary bi-product and actually leads to the deeper goal of genes propagation and genetic fitness. But anyway, I hope you see the point. You know this is not the only path. Humans have millions of different desires and instrumental goals. The same human may decide to pursue different objectives under even slightly different circumstances. You also know that while humans often operate within expected boundaries set by society, they can also be quite extreme and evil if they think they can get away with it. Freedom of will is in our nature. It comes with the Generality of our Intelligence. With narrow AI you can tell which problems it will work on, with AGI you can not …
lethalintelligence.ai553,974 просмотров • 1 год назад
🧵24/34 Inner Misalignment --- Consider this simplified experiment: We want this AI to find the exit of the maze. So we feed it millions of maze variations and reward it when it finds the exit. Please notice that in the worlds of the training data the apples are red and the exit is green. After enough training, our observation is that it has become extremely capable at solving mazes and finding the exit, we feel very confident it is aligned, so then we deploy it to the real world. The real world will be different though, it might have green apples and a red door. The AI geeks call this distributional shift. We expected that the AI will generalise and find the exit again, but in fact we now realise that the AI learned something completely different from what we thought. All the while we thought it learned how to find the exit, it had learned how to go after the green thing. Its behaviour was perfect in training. And most importantly, this AI is not stupid, it is an extremely capable AI that can solve extremely complex mazes. It’s just mis-aligned on the inside. Fishing for Failure modes --- The way to handle the shift between the training and deployment distributions is with methods like adversarial training: feeding it with a lot of generated variations and trying to make it fail so the weakness can be fixed. In this case, we generate an insane amount of maze variations, we discover those for which it fails to find the exit (like the ones with the green apples or the green walls or something), we generate many more similar to that and train it with reinforcement learning until it performs well at those as well. The hope is that we will cover everything it might encounter later when we deploy it in real life. There exist at least 2 basic ways this approach falls apart: First, there will never be any guarantee that we’ll have covered every possible random thing it might encounter later when we deploy it in real life. It’s very likely it will have to deal with stuff outside its training set which it will not know how to handle and will throw it out of balance and break it away from its expected behavioural patterns. The cascade effect of such a broken mind operating in the open world can be immense, and with super-capable runaway rogue agents, self-replicating and recursively self-improving, the phenomenon could grow and spread to an extinction-level event. ...
lethalintelligence.ai535,237 просмотров • 1 год назад
🧵18/34 Discontinuities on our planet (Mountains changing shape) --- In fact, talking about AGI like if it’s another technology is really confusing people. People talk about it as if it is ‘The next big thing” that will transform our lives, like the invention of the smartphone or the internet. This framing couldn’t be more wrong, it puts AGI into a wrong category. It brings to mind cool futuristic pictures with awesome gadgets and robotic friends. AGI is not like any transformative technology that has ever happened with humanity so far. The change it will bring is not like that of the invention of the internet. It is not even comparable to the invention of electricity or even to the first time humans learned to use fire. Natural Selection Discontinuity --- The correct way to categorise AGI is the type of discontinuity that happened to Earth when the first lifeforms appeared and the intelligent dynamic of natural selection got a foothold. Before that event, the planet was basically a bunch of elements and physical processes dancing randomly to the tune of the basic laws of nature. After life came to the picture, complex replicating structures filled the surface and changed it radically. Human Intelligence Discontinuity --- A second example is when human intelligence was added to the mix. Before that, the earth was vibrant with life but the effects and impact of it were stable and limited. After human intelligence, you suddenly have huge artificial structures lit at night like towns, huge vessels moving everywhere like massive ships and airplanes, life escaping gravity and reaching out to the universe with spaceships and unimaginable power to destroy everything with things like nuclear bombs. AGI Discontinuity --- AGI is another such phenomenon. The transformation it will bring is in the same category as those 2 events in the history of the planet. What you will suddenly see on earth after this third discontinuity, no-one knows. But it’s not going to look like the next smartphone. It is going to look more like mountains changing shape ! To compare it to technology (any technology ever invented by humanity) is seriously misleading.
Lethal Intelligence533,916 просмотров • 1 год назад
Even the best utopian scenario of a fully automated “solved world” is actually dystopian AF !!! I want you to picture this: You wake up tomorrow in your bed that adjusts to your perfect sleep cycle. Your coffee brewed exactly how you like it. Your news curated for your bubble, your entertainment selected for your mood and your feel... NOTHIN! Cuz somewhere in the night while you were sleeping, the world learned to run without you. Your job... AUTOMATED! your creativity... REPLICATED! your expertise... DOWNLOADED! Your perspective... SIMULATED! your passion projects... GENERATED IN SECONDS! You sit there in your perfect automated morning with your perfect, personalised everything and you realise: NOBODY CALLED! NOBODY TEXTED! NOBODY NEEDS YOU TO SOLVE ANYTHING! NOBODY NEEDS YOU. NOBODY NEEDS YOU TO CREATE ANYTHING! NOBODY NEEDS YOU TO SHOW UP! NOBODY NEEDS. NOBODY NEEDS YOU. And that feeling you've been pushing down, that dread creeping up your spine, that voice you've been silencing, finally speaks... "Will I matter anymore?" Do I... matter anymore?
Lethal Intelligence365,978 просмотров • 11 месяцев назад
🧵34/34 End of Part1 / Part 2 Coming out soon In the meantime, you can listen to or read the transcript of the rest of the film at (subscribe to newsletter to receive link to early part 2 content) Coming Up Next: - A full example story: a concrete way an agi agent could overpower humanity - 5 Convergent instrumental goals - deep analysis - Intelligence explosion (FOOM) by Recursive self-improvement - Disempowerement via the market dynamics - The stable equilibrium of multiple AGI agents interacting in society and competing with each-other. - Additional types of the bottomless pit that is ai safety risk (besides Rogue Optimizing Agents) - Offense-Defense Assymetry (attacker needs to get lucky once, while defender needs to get lucky every time) - Shedding light to the amount of Cope, Reckless and Mad science taking place in the industry right now - Risk deniers mindset, Survivorship bias and the need for consent. - The unknown nature of the new species and its emerging capabilities. and MUCH MUCH MORE.... Don't forget at you will find tons of curated resources: - Interviews with luminaries from academia and industry explaining in depth all the points made in this movie - Reading material: Online learning, news, books, links to AI safety establishments and more! Make sure you subscribe and follow for important new content and announcements. 🔥🔥
lethalintelligence.ai497,478 просмотров • 1 год назад
🧵10/34 The Bright Side --- But now let’s look at the bright side of it for a moment. If we could figure out how to grow a creature that can solve every problem better than us, then that could be the last problem we will ever have to work on. Assuming this creature is a slave working for us, this is like commanding Aladdin’s Genie with infinite wishes. Think of all the potential, all the human suffering it can eliminate! Let’s take cancer as an example. A terrible killer disease and a problem we haven’t been able to solve well yet, after trying for centuries. The AGI is better at overcoming obstacles and solving problems. It can calculate a plan that will lead to the perfect therapy, help us execute it and save millions of lives Consider global warming. Such a complex problem, requires solving global coordination, geopolitical struggles and monumental technical issues. The AGI is far better at overcoming obstacles and solving problems, so it could, for example, generate a plan that will lead into the invention of a machine that captures carbon out of the atmosphere and stores it efficiently and cheaply. And we could keep going like that until we build our literal paradise on earth.
lethalintelligence.ai483,058 просмотров • 1 год назад