hardmaru•This week
Interview with Juergen Schmidhuber, renowned ‘Father Of Modern AI’, says his life’s work won't lead to dystopia.
Schmidhuber interview expressing his views on the future of AI and AGI.
Original source. I think the interview is of interest to r/MachineLearning, and presents an alternate view, compared to other influential leaders in AI.
Juergen Schmidhuber, Renowned 'Father Of Modern AI,' Says His Life’s Work Won't Lead To Dystopia
May 23, 2023. Contributed by Hessie Jones.
Amid the growing concern about the impact of more advanced artificial intelligence (AI) technologies on society, there are many in the technology community who fear the implications of the advancements in Generative AI if they go unchecked. Dr. Juergen Schmidhuber, a renowned scientist, artificial intelligence researcher and widely regarded as one of the pioneers in the field, is more optimistic. He declares that many of those who suddenly warn against the dangers of AI are just seeking publicity, exploiting the media’s obsession with killer robots which has attracted more attention than “good AI” for healthcare etc.
The potential to revolutionize various industries and improve our lives is clear, as are the equal dangers if bad actors leverage the technology for personal gain. Are we headed towards a dystopian future, or is there reason to be optimistic? I had a chance to sit down with Dr. Juergen Schmidhuber to understand his perspective on this seemingly fast-moving AI-train that will leap us into the future.
As a teenager in the 1970s, Juergen Schmidhuber became fascinated with the idea of creating intelligent machines that could learn and improve on their own, becoming smarter than himself within his lifetime. This would ultimately lead to his groundbreaking work in the field of deep learning.
In the 1980s, he studied computer science at the Technical University of Munich (TUM), where he earned his diploma in 1987. His thesis was on the ultimate self-improving machines that, not only, learn through some pre-wired human-designed learning algorithm, but also learn and improve the learning algorithm itself. Decades later, this became a hot topic. He also received his Ph.D. at TUM in 1991 for work that laid some of the foundations of modern AI.
Schmidhuber is best known for his contributions to the development of recurrent neural networks (RNNs), the most powerful type of artificial neural network that can process sequential data such as speech and natural language. With his students Sepp Hochreiter, Felix Gers, Alex Graves, Daan Wierstra, and others, he published architectures and training algorithms for the long short-term memory (LSTM), a type of RNN that is widely used in natural language processing, speech recognition, video games, robotics, and other applications. LSTM has become the most cited neural network of the 20th century, and Business Week called it "arguably the most commercial AI achievement."
Throughout his career, Schmidhuber has received various awards and accolades for his groundbreaking work. In 2013, he was awarded the Helmholtz Prize, which recognizes significant contributions to the field of machine learning. In 2016, he was awarded the IEEE Neural Network Pioneer Award for "pioneering contributions to deep learning and neural networks." The media have often called him the “father of modern AI,” because the most cited neural networks all build on his lab’s work. He is quick to point out, however, that AI history goes back centuries.
Despite his many accomplishments, at the age of 60, he feels mounting time pressure towards building an Artificial General Intelligence within his lifetime and remains committed to pushing the boundaries of AI research and development. He is currently director of the KAUST AI Initiative, scientific director of the Swiss AI Lab IDSIA, and co-founder and chief scientist of AI company NNAISENSE, whose motto is "AI∀" which is a math-inspired way of saying "AI For All." He continues to work on cutting-edge AI technologies and applications to improve human health and extend human lives and make lives easier for everyone.
The following interview has been edited for clarity.
Jones: Thank you Juergen for joining me. You have signed letters warning about AI weapons. But you didn't sign the recent publication, "Pause Gigantic AI Experiments: An Open Letter"? Is there a reason?
Schmidhuber: Thank you Hessie. Glad to speak with you. I have realized that many of those who warn in public against the dangers of AI are just seeking publicity. I don't think the latest letter will have any significant impact because many AI researchers, companies, and governments will ignore it completely.
The proposal frequently uses the word "we" and refers to "us," the humans. But as I have pointed out many times in the past, there is no "we" that everyone can identify with. Ask 10 different people, and you will hear 10 different opinions about what is "good." Some of those opinions will be completely incompatible with each other. Don't forget the enormous amount of conflict between the many people.
The letter also says, "If such a pause cannot be quickly put in place, governments should intervene and impose a moratorium." The problem is that different governments have ALSO different opinions about what is good for them and for others. Great Power A will say, if we don't do it, Great Power B will, perhaps secretly, and gain an advantage over us. The same is true for Great Powers C and D.
Jones: Everyone acknowledges this fear surrounding current generative AI technology. Moreover, the existential threat of this technology has been publicly acknowledged by Sam Altman, CEO of OpenAI himself, calling for AI regulation. From your perspective, is there an existential threat?
Schmidhuber: It is true that AI can be weaponized, and I have no doubt that there will be all kinds of AI arms races, but AI does not introduce a new quality of existential threat. The threat coming from AI weapons seems to pale in comparison to the much older threat from nuclear hydrogen bombs that don’t need AI at all. We should be much more afraid of half-century-old tech in the form of H-bomb rockets. The Tsar Bomba of 1961 had almost 15 times more destructive power than all weapons of WW-II combined. Despite the dramatic nuclear disarmament since the 1980s, there are still more than enough nuclear warheads to wipe out human civilization within two hours, without any AI I’m much more worried about that old existential threat than the rather harmless AI weapons.
Jones: I realize that while you compare AI to the threat of nuclear bombs, there is a current danger that a current technology can be put in the hands of humans and enable them to “eventually” exact further harms to individuals of group in a very precise way, like targeted drone attacks. You are giving people a toolset that they've never had before, enabling bad actors, as some have pointed out, to be able to do a lot more than previously because they didn't have this technology.
Schmidhuber: Now, all that sounds horrible in principle, but our existing laws are sufficient to deal with these new types of weapons enabled by AI. If you kill someone with a gun, you will go to jail. Same if you kill someone with one of these drones. Law enforcement will get better at understanding new threats and new weapons and will respond with better technology to combat these threats. Enabling drones to target persons from a distance in a way that requires some tracking and some intelligence to perform, which has traditionally been performed by skilled humans, to me, it seems is just an improved version of a traditional weapon, like a gun, which is, you know, a little bit smarter than the old guns.
But, in principle, all of that is not a new development. For many centuries, we have had the evolution of better weaponry and deadlier poisons and so on, and law enforcement has evolved their policies to react to these threats over time. So, it's not that we suddenly have a new quality of existential threat and it's much more worrisome than what we have had for about six decades. A large nuclear warhead doesn’t need fancy face recognition to kill an individual. No, it simply wipes out an entire city with ten million inhabitants.
Jones: The existential threat that’s implied is the extent to which humans have control over this technology. We see some early cases of opportunism which, as you say, tends to get more media attention than positive breakthroughs. But you’re implying that this will all balance out?
Schmidhuber: Historically, we have a long tradition of technological breakthroughs that led to advancements in weapons for the purpose of defense but also for protection. From sticks, to rocks, to axes to gunpowder to cannons to rockets… and now to drones… this has had a drastic influence on human history but what has been consistent throughout history is that those who are using technology to achieve their own ends are themselves, facing the same technology because the opposing side is learning to use it against them. And that's what has been repeated in thousands of years of human history and it will continue. I don't see the new AI arms race as something that is remotely as existential a threat as the good old nuclear warheads.
You said something important, in that some people prefer to talk about the downsides rather than the benefits of this technology, but that's misleading, because 95% of all AI research and AI development is about making people happier and advancing human life and health.
Jones: Let’s touch on some of those beneficial advances in AI research that have been able to radically change present day methods and achieve breakthroughs.
Schmidhuber: All right! For example, eleven years ago, our team with my postdoc Dan Ciresan was the first to win a medical imaging competition through deep learning. We analyzed female breast cells with the objective to determine harmless cells vs. those in the pre-cancer stage. Typically, a trained oncologist needs a long time to make these determinations. Our team, who knew nothing about cancer, were able to train an artificial neural network, which was totally dumb in the beginning, on lots of this kind of data. It was able to outperform all the other methods. Today, this is being used not only for breast cancer, but also for radiology and detecting plaque in arteries, and many other things. Some of the neural networks that we have developed in the last 3 decades are now prevalent across thousands of healthcare applications, detecting Diabetes and Covid-19 and what not. This will eventually permeate across all healthcare. The good consequences of this type of AI are much more important than the click-bait new ways of conducting crimes with AI.
Jones: Adoption is a product of reinforced outcomes. The massive scale of adoption either leads us to believe that people have been led astray, or conversely, technology is having a positive effect on people’s lives.
Schmidhuber: The latter is the likely case. There's intense commercial pressure towards good AI rather than bad AI because companies want to sell you something, and you are going to buy only stuff you think is going to be good for you. So already just through this simple, commercial pressure, you have a tremendous bias towards good AI rather than bad AI. However, doomsday scenarios like in Schwarzenegger movies grab more attention than documentaries on AI that improve people’s lives.
Jones: I would argue that people are drawn to good stories – narratives that contain an adversary and struggle, but in the end, have happy endings. And this is consistent with your comment on human nature and how history, despite its tendency for violence and destruction of humanity, somehow tends to correct itself.
Let’s take the example of a technology, which you are aware – GANs – General Adversarial Networks, which today has been used in applications for fake news and disinformation. In actuality, the purpose in the invention of GANs was far from what it is used for today.
Schmidhuber: Yes, the name GANs was created in 2014 but we had the basic principle already in the early 1990s. More than 30 years ago, I called it artificial curiosity. It's a very simple way of injecting creativity into a little two network system. This creative AI is not just trying to slavishly imitate humans. Rather, it’s inventing its own goals. Let me explain:
You have two networks. One network is producing outputs that could be anything, any action. Then the second network is looking at these actions and it’s trying to predict the consequences of these actions. An action could move a robot, then something happens, and the other network is just trying to predict what will happen.
Now we can implement artificial curiosity by reducing the prediction error of the second network, which, at the same time, is the reward of the first network. The first network wants to maximize its reward and so it will invent actions that will lead to situations that will surprise the second network, which it has not yet learned to predict well.
In the case where the outputs are fake images, the first network will try to generate images that are good enough to fool the second network, which will attempt to predict the reaction of the environment: fake or real image, and it will try to become better at it. The first network will continue to also improve at generating images whose type the second network will not be able to predict. So, they fight each other. The 2nd network will continue to reduce its prediction error, while the 1st network will attempt to maximize it.
Through this zero-sum game the first network gets better and better at producing these convincing fake outputs which look almost realistic. So, once you have an interesting set of images by Vincent Van Gogh, you can generate new images that leverage his style, without the original artist having ever produced the artwork himself.
Jones: I see how the Van Gogh example can be applied in an education setting and there are countless examples of artists mimicking styles from famous painters but image generation from this instance that can happen within seconds is quite another feat. And you know this is how GANs has been used. What’s more prevalent today is a socialized enablement of generating images or information to intentionally fool people. It also surfaces new harms that deal with the threat to intellectual property and copyright, where laws have yet to account for. And from your perspective this was not the intention when the model was conceived. What was your motivation in your early conception of what is now GANs?
Schmidhuber: My old motivation for GANs was actually very important and it was not to create deepfakes or fake news but to enable AIs to be curious and invent their own goals, to make them explore their environment and make them creative.
Suppose you have a robot that executes one action, then something happens, then it executes another action, and so on, because it wants to achieve certain goals in the environment. For example, when the battery is low, this will trigger “pain” through hunger sensors, so it wants to go to the charging station, without running into obstacles, which will trigger other pain sensors. It will seek to minimize pain (encoded through numbers). Now the robot has a friend, the second network, which is a world model ––it’s a prediction machine that learns to predict the consequences of the robot’s actions.
Once the robot has a good model of the world, it can use it for planning. It can be used as a simulation of the real world. And then it can determine what is a good action sequence. If the robot imagines this sequence of actions, the model will predict a lot of pain, which it wants to avoid. If it plays this alternative action sequence in its mental model of the world, then it will predict a rewarding situation where it’s going to sit on the charging station and its battery is going to load again. So, it'll prefer to execute the latter action sequence.
In the beginning, however, the model of the world knows nothing, so how can we motivate the first network to generate experiments that lead to data that helps the world model learn something it didn’t already know? That’s what artificial curiosity is about. The dueling two network systems effectively explore uncharted environments by creating experiments so that over time the curious AI gets a better sense of how the environment works. This can be applied to all kinds of environments, and has medical applications.
Jones: Let’s talk about the future. You have said, “Traditional humans won’t play a significant role in spreading intelligence across the universe.”
Schmidhuber: Let’s first conceptually separate two types of AIs. The first type of AI are tools directed by humans. They are trained to do specific things like accurately detect diabetes or heart disease and prevent attacks before they happen. In these cases, the goal is coming from the human. More interesting AIs are setting their own goals. They are inventing their own experiments and learning from them. Their horizons expand and eventually they become more and more general problem solvers in the real world. They are not controlled by their parents, but much of what they learn is through self-invented experiments.
A robot, for example, is rotating a toy, and as it is doing this, the video coming in through the camera eyes, changes over time and it begins to learn how this video changes and learns how the 3D nature of the toy generates certain videos if you rotate it a certain way, and eventually, how gravity works, and how the physics of the world works. Like a little scientist!
And I have predicted for decades that future scaled-up versions of such AI scientists will want to further expand their horizons, and eventually go where most of the physical resources are, to build more and bigger AIs. And of course, almost all of these resources are far away from earth out there in space, which is hostile to humans but friendly to appropriately designed AI-controlled robots and self-replicating robot factories. So here we are not talking any longer about our tiny biosphere; no, we are talking about the much bigger rest of the universe. Within a few tens of billions of years, curious self-improving AIs will colonize the visible cosmos in a way that’s infeasible for humans. Those who don’t won’t have an impact. Sounds like science fiction, but since the 1970s I have been unable to see a plausible alternative to this scenario, except for a global catastrophe such as an all-out nuclear war that stops this development before it takes off.
Jones: How long have these AIs, which can set their own goals — how long have they existed? To what extent can they be independent of human interaction?
Schmidhuber: Neural networks like that have existed for over 30 years. My first simple adversarial neural network system of this kind is the one from 1990 described above. You don’t need a teacher there; it's just a little agent running around in the world and trying to invent new experiments that surprise its own prediction machine.
Once it has figured out certain parts of the world, the agent will become bored and will move on to more exciting experiments. The simple 1990 systems I mentioned have certain limitations, but in the past three decades, we have also built more sophisticated systems that are setting their own goals and such systems I think will be essential for achieving true intelligence. If you are only imitating humans, you will never go beyond them. So, you really must give AIs the freedom to explore previously unexplored regions of the world in a way that no human is really predefining.
Jones: Where is this being done today?
Schmidhuber: Variants of neural network-based artificial curiosity are used today for agents that learn to play video games in a human-competitive way. We have also started to use them for automatic design of experiments in fields such as materials science. I bet many other fields will be affected by it: chemistry, biology, drug design, you name it. However, at least for now, these artificial scientists, as I like to call them, cannot yet compete with human scientists.
I don’t think it’s going to stay this way but, at the moment, it’s still the case. Sure, AI has made a lot of progress. Since 1997, there have been superhuman chess players, and since 2011, through the DanNet of my team, there have been superhuman visual pattern recognizers. But there are other things where humans, at the moment at least, are much better, in particular, science itself. In the lab we have many first examples of self-directed artificial scientists, but they are not yet convincing enough to appear on the radar screen of the public space, which is currently much more fascinated with simpler systems that just imitate humans and write texts based on previously seen human-written documents.
Jones: You speak of these numerous instances dating back 30 years of these lab experiments where these self-driven agents are deciding and learning and moving on once they’ve learned. And I assume that that rate of learning becomes even faster over time. What kind of timeframe are we talking about when this eventually is taken outside of the lab and embedded into society?
Schmidhuber: This could still take months or even years :-) Anyway, in the not-too-distant future, we will probably see artificial scientists who are good at devising experiments that allow them to discover new, previously unknown physical laws.
As always, we are going to profit from the old trend that has held at least since 1941: every decade compute is getting 100 times cheaper.
Jones: How does this trend affect modern AI such as ChatGPT?
Schmidhuber: Perhaps you know that all the recent famous AI applications such as ChatGPT and similar models are largely based on principles of artificial neural networks invented in the previous millennium. The main reason why they works so well now is the incredible acceleration of compute per dollar.
ChatGPT is driven by a neural network called “Transformer” described in 2017 by Google. I am happy about that because a quarter century earlier in 1991 I had a particular Transformer variant which is now called the “Transformer with linearized self-attention”. Back then, not much could be done with it, because the compute cost was a million times higher than today. But today, one can train such models on half the internet and achieve much more interesting results.
Jones: And for how long will this acceleration continue?
Schmidhuber: There's no reason to believe that in the next 30 years, we won't have another factor of 1 million and that's going to be really significant. In the near future, for the first time we will have many not-so expensive devices that can compute as much as a human brain. The physical limits of computation, however, are much further out so even if the trend of a factor of 100 every decade continues, the physical limits (of 1051 elementary instructions per second and kilogram of matter) won’t be hit until, say, the mid-next century. Even in our current century, however, we’ll probably have many machines that compute more than all 10 billion human brains collectively and you can imagine, everything will change then!
Jones: That is the big question. Is everything going to change? If so, what do you say to the next generation of leaders, currently coming out of college and university. So much of this change is already impacting how they study, how they will work, or how the future of work and livelihood is defined. What is their purpose and how do we change our systems so they will adapt to this new version of intelligence?
Schmidhuber: For decades, people have asked me questions like that, because you know what I'm saying now, I have basically said since the 1970s, it’s just that today, people are paying more attention because, back then, they thought this was science fiction.
They didn't think that I would ever come close to achieving my crazy life goal of building a machine that learns to become smarter than myself such that I can retire. But now many have changed their minds and think it's conceivable. And now I have two daughters, 23 and 25. People ask me: what do I tell them? They know that Daddy always said, “It seems likely that within your lifetimes, you will have new types of intelligence that are probably going to be superior in many ways, and probably all kinds of interesting ways.” How should they prepare for that? And I kept telling them the obvious: Learn how to learn new things! It's not like in the previous millennium where within 20 years someone learned to be a useful member of society, and then took a job for 40 years and performed in this job until she received her pension. Now things are changing much faster and we must learn continuously just to keep up. I also told my girls that no matter how smart AIs are going to get, learn at least the basics of math and physics, because that’s the essence of our universe, and anybody who understands this will have an advantage, and learn all kinds of new things more easily. I also told them that social skills will remain important, because most future jobs for humans will continue to involve interactions with other humans, but I couldn’t teach them anything about that; they know much more about social skills than I do.
You touched on the big philosophical question about people’s purpose. Can this be answered without answering the even grander question: What’s the purpose of the entire universe?
We don’t know. But what’s happening right now might be connected to the unknown answer. Don’t think of humans as the crown of creation. Instead view human civilization as part of a much grander scheme, an important step (but not the last one) on the path of the universe from very simple initial conditions towards more and more unfathomable complexity. Now it seems ready to take its next step, a step comparable to the invention of life itself over 3.5 billion years ago. Alas, don’t worry, in the end, all will be good!
Jones: Let’s get back to this transformation happening right now with OpenAI. There are many questioning the efficacy and accuracy of ChatGPT, and are concerned its release has been premature. In light of the rampant adoption, educators have banned its use over concerns of plagiarism and how it stifles individual development. Should large language models like ChatGPT be used in school?
Schmidhuber: When the calculator was first introduced, instructors forbade students from using it in school. Today, the consensus is that kids should learn the basic methods of arithmetic, but they should also learn to use the “artificial multipliers” aka calculators, even in exams, because laziness and efficiency is a hallmark of intelligence. Any intelligent being wants to minimize its efforts to achieve things.
And that's the reason why we have tools, and why our kids are learning to use these tools. The first stone tools were invented maybe 3.5 million years ago; tools just have become more sophisticated over time. In fact, humans have changed in response to the properties of their tools. Our anatomical evolution was shaped by tools such as spears and fire. So, it's going to continue this way. And there is no permanent way of preventing large language models from being used in school.
Jones: And when our children, your children graduate, what does their future work look like?
Schmidhuber: A single human trying to predict details of how 10 billion people and their machines will evolve in the future is like a single neuron in my brain trying to predict what the entire brain and its tens of billions of neurons will do next year. 40 years ago, before the WWW was created at CERN in Switzerland, who would have predicted all those young people making money as YouTube video bloggers?
Nevertheless, let’s make a few limited job-related observations. For a long time, people have thought that desktop jobs may require more intelligence than skills trade or handicraft professions. But now, it turns out that it's much easier to replace certain aspects of desktop jobs than replacing a carpenter, for example. Because everything that works well in AI is happening behind the screen currently, but not so much in the physical world.
There are now artificial systems that can read lots of documents and then make really nice summaries of these documents. That is a desktop job. Or you give them a description of an illustration that you want to have for your article and pretty good illustrations are being generated that may need some minimal fine-tuning. But you know, all these desktop jobs are much easier to facilitate than the real tough jobs in the physical world. And it's interesting that the things people thought required intelligence, like playing chess, or writing or summarizing documents, are much easier for machines than they thought. But for things like playing football or soccer, there is no physical robot that can remotely compete with the abilities of a little boy with these skills. So, AI in the physical world, interestingly, is much harder than AI behind the screen in virtual worlds. And it's really exciting, in my opinion, to see that jobs such as plumbers are much more challenging than playing chess or writing another tabloid story.
Jones: The way data has been collected in these large language models does not guarantee personal information has not been excluded. Current consent laws already are outdated when it comes to these large language models (LLM). The concern, rightly so, is increasing surveillance and loss of privacy. What is your view on this?
Schmidhuber: As I have indicated earlier: are surveillance and loss of privacy inevitable consequences of increasingly complex societies? Super-organisms such as cities and states and companies consist of numerous people, just like people consist of numerous cells. These cells enjoy little privacy. They are constantly monitored by specialized "police cells" and "border guard cells": Are you a cancer cell? Are you an external intruder, a pathogen? Individual cells sacrifice their freedom for the benefits of being part of a multicellular organism.
Similarly, for super-organisms such as nations. Over 5000 years ago, writing enabled recorded history and thus became its inaugural and most important invention. Its initial purpose, however, was to facilitate surveillance, to track citizens and their tax payments. The more complex a super-organism, the more comprehensive its collection of information about its constituents.
200 years ago, at least, the parish priest in each village knew everything about all the village people, even about those who did not confess, because they appeared in the confessions of others. Also, everyone soon knew about the stranger who had entered the village, because some occasionally peered out of the window, and what they saw got around. Such control mechanisms were temporarily lost through anonymization in rapidly growing cities but are now returning with the help of new surveillance devices such as smartphones as part of digital nervous systems that tell companies and governments a lot about billions of users. Cameras and drones etc. are becoming increasingly tinier and more ubiquitous. More effective recognition of faces and other detection technology are becoming cheaper and cheaper, and many will use it to identify others anywhere on earth; the big wide world will not offer any more privacy than the local village. Is this good or bad? Some nations may find it easier than others to justify more complex kinds of super-organisms at the expense of the privacy rights of their constituents.
Jones: So, there is no way to stop or change this process of collection, or how it continuously informs decisions over time? How do you see governance and rules responding to this, especially amid Italy’s ban on ChatGPT following suspected user data breach and the more recent news about the Meta’s record $1.3billion fine in the company’s handling of user information?
Schmidhuber: Data collection has benefits and drawbacks, such as the loss of privacy. How to balance those? I have argued for addressing this through data ownership in data markets. If it is true that data is the new oil, then it should have a price, just like oil. At the moment, the major surveillance platforms such as Meta do not offer users any money for their data and the transitive loss of privacy. In the future, however, we will likely see attempts at creating efficient data markets to figure out the data's true financial value through the interplay between supply and demand.
Even some of the sensitive medical data should not be priced by governmental regulators but by patients (and healthy persons) who own it and who may sell or license parts thereof as micro-entrepreneurs in a healthcare data market.
Following a previous interview, I gave for one of the largest re-insurance companies , let's look at the different participants in such a data market: patients, hospitals, data companies. (1) Patients with a rare form of cancer can offer more valuable data than patients with a very common form of cancer. (2) Hospitals and their machines are needed to extract the data, e.g., through magnet spin tomography, radiology, evaluations through human doctors, and so on. (3) Companies such as Siemens, Google or IBM would like to buy annotated data to make better artificial neural networks that learn to predict pathologies and diseases and the consequences of therapies. Now the market’s invisible hand will decide about the data’s price through the interplay between demand and supply. On the demand side, you will have several companies offering something for the data, maybe through an app on the smartphone (a bit like a stock market app). On the supply side, each patient in this market should be able to profit from high prices for rare valuable types of data. Likewise, competing data extractors such as hospitals will profit from gaining recognition and trust for extracting data well at a reasonable price. The market will make the whole system efficient through incentives for all who are doing a good job. Soon there will be a flourishing ecosystem of commercial data market advisors and what not, just like the ecosystem surrounding the traditional stock market. The value of the data won’t be determined by governments or ethics committees, but by those who own the data and decide by themselves which parts thereof they want to license to others under certain conditions.
At first glance, a market-based system seems to be detrimental to the interest of certain monopolistic companies, as they would have to pay for the data - some would prefer free data and keep their monopoly. However, since every healthy and sick person in the market would suddenly have an incentive to collect and share their data under self-chosen anonymity conditions, there will soon be many more useful data to evaluate all kinds of treatments. On average, people will live longer and healthier, and many companies and the entire healthcare system will benefit.
Jones: Finally, what is your view on open source versus the private companies like Google and OpenAI? Is there a danger to supporting these private companies’ large language models versus trying to keep these models open source and transparent, very much like what LAION is doing?
Schmidhuber: I signed this open letter by LAION because I strongly favor the open-source movement. And I think it's also something that is going to challenge whatever big tech dominance there might be at the moment. Sure, the best models today are run by big companies with huge budgets for computers, but the exciting fact is that open-source models are not so far behind, some people say maybe six to eight months only. Of course, the private company models are all based on stuff that was created in academia, often in little labs without so much funding, which publish without patenting their results and open source their code and others take it and improved it.
Big tech has profited tremendously from academia; their main achievement being that they have scaled up everything greatly, sometimes even failing to credit the original inventors.
So, it's very interesting to see that as soon as some big company comes up with a new scaled-up model, lots of students out there are competing, or collaborating, with each other, trying to come up with equal or better performance on smaller networks and smaller machines. And since they are open sourcing, the next guy can have another great idea to improve it, so now there’s tremendous competition also for the big companies.
Because of that, and since AI is still getting exponentially cheaper all the time, I don't believe that big tech companies will dominate in the long run. They find it very hard to compete with the enormous open-source movement. As long as you can encourage the open-source community, I think you shouldn't worry too much. Now, of course, you might say if everything is open source, then the bad actors also will more easily have access to these AI tools. And there's truth to that. But as always since the invention of controlled fire, it was good that knowledge about how technology works quickly became public such that everybody could use it. And then, against any bad actor, there's almost immediately a counter actor trying to nullify his efforts. You see, I still believe in our old motto "AI∀" or "AI For All."
Jones: Thank you, Juergen for sharing your perspective on this amazing time in history. It’s clear that with new technology, the enormous potential can be matched by disparate and troubling risks which we’ve yet to solve, and even those we have yet to identify. If we are to dispel the fear of a sentient system for which we have no control, humans, alone need to take steps for more responsible development and collaboration to ensure AI technology is used to ultimately benefit society. Humanity will be judged by what we do next.
![Zero To One [Book Review]](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/startups_Introduction_to_AI_20250328_192047_processed_image.jpg)
![The case for micro PE [x-post from r/micro_pe]](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/smallbusiness_AI_for_SMB_20250328_184737_processed_image.jpg)
![[P] Building an Reinforcement Learning Agent to play The Legend of Zelda](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/MachineLearning_No-code_AI_20250328_190652_processed_image.jpg)
![[P] [R] sANNd: A New Neural Network Framework Using Trainable Iterators](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/MachineLearning_No-code_AI_20250328_190640_processed_image.jpg)
![[N] Netflix and European Space Agency no longer working with Siraj Raval](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/MachineLearning_No-code_AI_20250328_190611_processed_image.jpg)
![[R] Analysis of 400+ ML competitions in 2024](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/MachineLearning_No-code_AI_20250328_190616_processed_image.jpg)
![[N] 20 hours of new lectures on Deep Learning and Reinforcement Learning with lots of examples](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/MachineLearning_Introduction_to_AI_20250328_192244_processed_image.jpg)
![[D] I tried the new Gemini API - it automatically stops when generating "OpenAI" or "GPT" lol](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/MachineLearning_Introduction_to_AI_20250328_192227_processed_image.jpg)
![[D] Advanced courses update](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/MachineLearning_Introduction_to_AI_20250328_192224_processed_image.jpg)
![[N] How Stability AI’s Founder Tanked His Billion-Dollar Startup](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/MachineLearning_Introduction_to_AI_20250328_192205_processed_image.jpg)
![[D] AI Agents: too early, too expensive, too unreliable](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/MachineLearning_AI_strategy_20250328_191812_processed_image.jpg)
![[D] What do you think of Mistral.ai's value proposition and open source strategy?](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/MachineLearning_AI_strategy_20250328_191800_processed_image.jpg)
![[N] How Stability AI’s Founder Tanked His Billion-Dollar Startup](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/MachineLearning_AI_strategy_20250328_191753_processed_image.jpg)
![[Discussion]: Mark Zuckerberg on Meta's Strategy on Open Source and AI during the earnings call](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/MachineLearning_AI_strategy_20250328_191745_processed_image.jpg)
![[D] Playing big league at home on a budget?](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/MachineLearning_AI_implementation_for_beginners_20250328_190039_processed_image.jpg)
![[P] My deep learning library from sophomore year in high school](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/MachineLearning_AI_implementation_for_beginners_20250328_190049_processed_image.jpg)
![[D] What are some good advanced platforms?](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/MachineLearning_AI_implementation_for_beginners_20250328_190028_processed_image.jpg)
![Andrej Karpathy releases concise GPT implementation. Why has he bothered to do this: doesn't he work for OpenAI, at least indirectly? [D] [N]](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/MachineLearning_AI_implementation_20250328_185843_processed_image.jpg)
![[N] How Stability AI’s Founder Tanked His Billion-Dollar Startup](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/MachineLearning_AI_for_non-technical_founders_20250328_192607_processed_image.jpg)
![[R] From 3D Contour Plots to AI-Generated Art](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/MachineLearning_AI_for_digital_automation_20250328_184558_processed_image.jpg)
![[P] I built an open SotA image tagging model to do what CLIP won't](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/MachineLearning_AI_for_business_20250328_183457_processed_image.jpg)
![[Discussion]: Mark Zuckerberg on Meta's Strategy on Open Source and AI during the earnings call](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/MachineLearning_AI_for_business_20250328_183439_processed_image.jpg)
![[D] A Jobless Rant - ML is a Fool's Gold](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/MachineLearning_AI_for_business_20250328_183436_processed_image.jpg)
![[N] How Stability AI’s Founder Tanked His Billion-Dollar Startup](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/MachineLearning_AI_for_business_20250328_183412_processed_image.jpg)
![[D] AI Agents: too early, too expensive, too unreliable](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/MachineLearning_AI_automation_tools_20250328_191213_processed_image.jpg)
![[P] I made an automation to launch AI Tools with 100+ AI Directories](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/MachineLearning_AI_automation_tools_20250328_191158_processed_image.jpg)
![[CASE STUDY] From 217/m to $2,836/m in 9 months - Sold for $59,000; I grow and monetise web traffic of 5, 6, 7 figures USD valued passive income content sites [AMA]](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/Entrepreneur_Introduction_to_AI_20250328_191948_processed_image.jpg)
![Where Do I Find Like-Minded, Unorthodox Co-founders? [Tech]](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/Entrepreneur_AI_for_non-technical_founders_20250328_192357_processed_image.jpg)
![[CASE STUDY] From 217/m to $2,836/m in 9 months - Sold for $59,000; I grow and monetise web traffic of 5, 6, 7 figures USD valued passive income content sites [AMA]](https://jfbmhhfxbbrxcmwilqxt.supabase.co/storage/v1/object/public/resource-images/Entrepreneur_AI_for_digital_automation_20250328_184217_processed_image.jpg)
