Nvidia introduced its new compact generative AI supercomputer, the Jetson Orin Nano Super. What is its significance? What is Artificial General Intelligence (AGI)?
Nvidia has defined its latest offering as a ‘“compact, yet powerful computer” that redefines generative AI for small edge devices. When it comes to performances, the Justin Orin Nano Super delivers up to 67 TOPS of AI, which is a 1.7 times improvement when compared to its predecessor.
TOPS or Trillions of Operations Per Second, is a key indicator to measure the computational prowess of AI chips and NPU chips (neural processing unit chips that mimic the human brain’s neural network, which is designed to accelerate AI tasks).
The supercomputer is capable of running some of the most popular generative AI models such as vision transformers, large language models, vision-language models, etc. It features a memory bandwidth of 102 GB/s and CPU frequency of 1.7 GHZ.
The computer does not come with built-in storage, and a user may be required to download the operating system to a microSD card to boot the system, much similar to a Raspberry Pie.
The Jetson Orin Nano Super Developer Kit, although tiny, can help developers unravel an assortment of applications across industries. It can be put to use in a plethora of scenarios such as smart surveillance systems, robotics, smart retail, healthcare, AI-powered smart home devices and wearables, autonomous vehicles, research and education, content creation, etc.
Supercomputer
A supercomputer is a large computing system specifically designed to solve complex, scientific and industrial challenges, which tend to be time-consuming and computation-intensive.
They are used in quantum mechanics, weapons research, weather forecasting and climate research, oil and gas exploration, molecular dynamics and physical simulations, data analytics and big data — all of which require a high computing capacity which are unavailable with regular systems.
Artificial General Intelligence (AGI)
AGI refers to a machine or a software that can perform any intellectual task that a human can do. This includes reasoning, common sense, abstract thinking, background knowledge, transfer learning, ability to differentiate between cause and effect, etc.
In simple words, AGI aims to emulate human cognitive abilities such that it allows it to do unfamiliar tasks, learn from new experiences, and apply its knowledge in new ways.
The main difference between AGI and the more common form of AI, also known as narrow AI, lies in their scope and capabilities.
Narrow AI is designed to perform specific tasks such as image recognition, translation, or even playing games like chess—at which it can outdo humans, but it remains limited to its set parameters. On the other hand, AGI envisions a broader, more generalised form of intelligence, not confined to any particular task (like humans).
