AI and the data center 

The interest in AI has skyrocketed thanks in large to the rise of new AI models that have the potential to change the nature of industries on a global scale. With how data intensive AI is, its soaring popularity has also kickstarted a potential billion-dollar spending campaign on data centers. Let’s explore the basics of AI, its rising popularity, and how the data center drives the next generation of AI.  

Background on AI

A common question/talking point for the general population when discussing artificial intelligence, is simply: “What is Artificial Intelligence?” To many people, AI should behave like a human-like robot, akin to something out of an 80's or 90's science fiction movie. Others, particularly AI developers, tend to think of AI as an advanced tool to solve problems. We let an AI model answer this question itself:

Question: 

What is Artificial Intelligence?

Answer from AI: 

Artificial Intelligence (AI) is the ability of machines to perform tasks that would normally require human intelligence such as visual perception, speech recognition, decision-making, and language translation. AI is a set of technologies that enable computers to perform a variety of advanced functions, including the ability to see, understand and translate spoken and written language, analyze data, make recommendations, and more. AI is an academic discipline with various views on what constitutes its area of research, goals and approaches used.

Artificial Intelligence is a very broad term that encompasses a wide range of categories and applications. Because the expectations for AI range from the practical to the more ambitious, AI models are often categorized based on their applications.

Generative AI

Recent advancements in AI have been in a subcategory of AI called Generative AI. This is a type of AI that is able to produce content that ranges from text, images, video, audio, and 3D models, based on prompts. In other words, the AI model can take an input of questions or instructions and output content with that information. 

Generative AI models are able to accomplish this through the utilization of transformer models, which are artificial neural networks that can “learn” context. Transformer architectures contain both an encoder and a decoder. The encoder takes a question or set of instructions and simplifies the question/instructions to make them more concise. The decoder then takes this simplified version and uses an algorithm called Self-Attention to assign weighted values to each word based on its importance to the sentence. 

Take the sentence “What are the best restaurants around this area?” for example. The AI model can weigh the terms ‘restaurants’ ‘best’ and ‘around’ more heavily compared to the other words. The model then highlights ‘restaurants’ as the main topic of the sentence and works from there, enabling it to “understand” the context of the question. The model is able to assign relatively accurate weighted values to words because it has been pre-trained on a massive amount of data from the internet, including trillions of text, code, etc. It then uses word prediction based on the previous context to generate additional text. 

Evolving AI

So, what is the hype about current AI models all about? Why have recent AI models generated so much interest?  

Much of the hype around these AI models stems from their ability to tackle complex tasks such as writing emails, essays, coding/debugging and more. Generative AI models are able to produce content with high coherency, which would normally require a human to do so. To illustrate their potency, here we demonstrate what current iterations of AI are able to do with simple prompts. 

As a follow-up instruction to the original question that was asked earlier, we asked the AI model to explain to a kid what AI is.

Artificial Intelligence (AI) is when computers and machines can do things that normally require human intelligence like learning, seeing, hearing, and decision-making. It’s like having a robot friend who can help you with your homework or play games with you. Just like how you learn new things every day, AI can also learn new things every day by looking at pictures and listening to sounds. AI is really smart and can help people do things faster and better than before.

In addition to producing conversational-like text with high coherency and being able to adjust the content for different audiences, AI models can also generate photos or photoshop to an impressive degree. Compare and contrast original photos and AI photos. For example:

Original Photo:

AI photoshopped photo with prompt: Same person outside in a field