Liquid Neural Networks: A New Era of Understandable AI

Ramin Hasani envisions AI as a flexible, understandable ally that can solve complex global issues.

### Designing Friendly AI: The Vision of Liquid Neural Networks
* 🤖 Ramin Hasani, cofounder and CEO of Liquid AI, dreams of creating artificial intelligence that acts as a **friend** and can solve **complex global issues**, such as understanding **mathematics** and **humanitarian sciences**.
* 💡 He believes that an AI system capable of **comprehending physics** could address the energy crisis, ultimately helping humans become **better versions of themselves**.
* 🔬 Liquid AI is built on "**liquid neural networks**," a technology invented by Hasani at MIT, which offers **flexible intelligence** compared to traditional fixed AI systems.
* 🧠 Inspired by the feedback mechanisms in human brains and the genome of the tiny worm "C. elegans," these networks can **adapt and change responses based on input**, enhancing their **problem-solving capabilities**.
* 🌱 Nature's evolutionary processes provide a shortcut for developing efficient algorithms, allowing Liquid AI to create intelligent systems that can **evolve beyond human capabilities**.
* 📊 Unlike traditional AI systems that function as black boxes, Liquid's approach emphasizes **transparency**, enabling a **deeper understanding** of how these systems operate and ensuring **better control** over their actions.
* 🛡 Hasani emphasizes the importance of **maintaining control over superintelligent systems**, noting that the potential benefits of such technology come with the **responsibility to manage it effectively**.
* 🌍 Ultimately, Liquid AI aims to demonstrate that **powerful AI can coexist with human oversight**, alleviating fears surrounding the technology's **scalability and impact on society**.

My wildest dream is to design artificial intelligence that is our friend, you know. If you have an AI system that helps us understand mathematics, you can solve the economy of the world. If you have an AI system that can understand humanitarian sciences, we can actually solve all of our conflicts. I want this system to, given Einstein’s and Maxwell’s equations, take it and solve new physics, you know. If you understand physics, you can solve the energy problem. So you can actually design ways for humans to be the better versions of themselves. I'm Ramin Hasani. I’m the cofounder and CEO of Liquid AI. Liquid AI is an AI company built on top of a technology that I invented back at MIT. It’s called “liquid neural networks.” These are a form of flexible intelligence, as opposed to today's AI systems that are fixed, basically. So think about your brain. You can change your thoughts. When somebody talks to you,

you can completely change the way you respond. You always have a mechanism that we call feedback in your system. So basically when you receive information from someone as an input, you basically process that information, and then you reply. For liquid neural networks, we simply got those feedback mechanisms, and we added that to the system. So that means it has the ability of thinking. That property is inspired by nature. We looked into the brains of animals and, in particular, a very, very tiny worm called “C. elegans.” The fascinating fact about the brain of the worm is that it shares 75 percent of the genome that it has with humans. We have the entire genome mapped. So we understand a whole lot about the functionality of its nervous system as well. So if you understand the properties of cells in the worm, maybe we can build intelligent systems that are as good as the worm and then evolve them into systems that are better than even humans.

The reason why we are studying nature is the fact that we can actually have a shortcut through exploring all the possible kinds of algorithms that you can design. You can look into nature; that would give you a shortcut to really faster get into efficient algorithms because nature has done a lot of search, billions of years of evolution, right? So, we learned so much from those principles. I just brought a tiny principle from the worm into artificial neural networks. And now they are flexible, and they can solve problems in an explainable way that was not possible before. AI is becoming very capable, right? The reason why AI is hard to regulate is that we cannot understand, even the people who design the systems, we don't understand those systems. They are black boxes. With Liquid, because we are fundamentally using mathematics that are understandable, we have tools to really understand and pinpoint which part of the system is responsible for what; you're designing white box systems.

So if you have systems that you can understand their behavior, that means even if you scale them into something very, very intelligent, you can always have a lot of control over that system because you understand it. You can never let it go rogue. So all of the crises we are dealing with right now, you know, doomsday kind of scenarios, is all about scaling a technology that we don't understand. With Liquid, our purpose is to really calm people down and show people that, hey, you can have very powerful systems, that you have a lot of control and visibility into their working mechanisms. The gift of having something [with] superintelligence is massive, and it can enable a lot of things for us. But at the same time, we need to have control over that technology. Because this is the first time that we’re going to have a technology that is going to be better than all of humanity combined.

How a Worm Could Save Humanity From Bad AI | Ramin Hasani | TED

The TED Talks channel features the best talks and performances from the TED Conference, where the world's leading thinkers and doers give the talk of their lives in 18 minutes (or less). Look for talks on Technology, Entertainment and Design -- plus science, business, global issues, the arts and more. You're welcome to link to or embed these videos, forward them to others and share these ideas with people you know.

TED's videos may be used for non-commercial purposes under a Creative Commons License, Attribution–Non Commercial–No Derivatives (or the CC BY – NC – ND 4.0 International) and in accordance with our TED Talks Usage Policy: https://www.ted.com/about/our-organization/our-policies-terms/ted-talks-usage-policy. For more information on using TED for commercial purposes (e.g. employee learning, in a film or online course), please submit a Media Request at https://media-requests.ted.com

Designing Friendly Artificial Intelligence

Ramin Hasani, cofounder and CEO of Liquid AI, aims to create AI systems that can solve global issues by understanding mathematics and humanitarian sciences.

Liquid AI's technology, liquid neural networks, offers flexible intelligence by incorporating feedback mechanisms, similar to how the human brain functions.

The company's inspiration comes from the C.

elegans worm, which shares 75% of its genome with humans, with the goal of evolving intelligent systems that surpass human capabilities.

Learning from Nature to Design AI Algorithms

Studying nature provides a shortcut to designing efficient algorithms, as evolution has conducted billions of years of search.

The principles learned from nature have led to the development of flexible artificial neural networks that can solve problems in an explainable way.

Liquid's approach, using understandable mathematics, allows for the design of white box systems, providing clarity and understanding of the system's functionality.

The Importance of Understanding and Controlling Intelligent Systems

Understanding the behavior of systems is crucial for maintaining control, even as they scale to higher intelligence.

The current crises are largely due to the rapid scaling of technology that is not well understood.

Liquid's purpose is to provide powerful systems with transparency and control, emphasizing the need for oversight as we approach superintelligent technology.