Real Sheldon: a Science Blog

A Machine Learning algorithm walks into a bar. The bartender asks “What will you have?”. The algorithm says “What’s everyone else having?”

How does an AI apologize?
“I’m sorry, I can’t compute my behavior.”

The funny part is that these jokes were actually invented by a very famous AI Chatbot, ChatGPT. I simply wrote:” write a joke about AI” and the algorithm typed this. But, when was all this invented? And, how does it work?

A Brief History

Datas taken from the Harvard University blog “The History of Artificial Intelligence”

AI is a tool. The choice about how it gets deployed is ours.

Oren Etzioni

In the first half of the 20^th century, science fiction familiarized the world with the concept of artificially intelligent robots. It began with the “heartless” Tin man from the Wizard of Oz and continued with the humanoid robot that impersonated Maria in Metropolis. By the 1950s, we had a generation of scientists, mathematicians, and philosophers with the concept of artificial intelligence (or AI) culturally assimilated in their minds. One such person was Alan Turing, a young British polymath who explored the mathematical possibility of artificial intelligence. Turing suggested that humans use available information as well as reason in order to solve problems and make decisions, so why can’t machines do the same thing? This was the logical framework of his 1950 paper, Computing Machinery and Intelligence in which he discussed how to build intelligent machines and how to test their intelligence.

Breaching the initial fog of AI revealed a mountain of obstacles. The biggest was the lack of computational power to do anything substantial: computers simply couldn’t store enough information or process it fast enough. In order to communicate, for example, one needs to know the meanings of many words and understand them in many combinations. Hans Moravec, a doctoral student of McCarthy at the time, stated that “computers were still millions of times too weak to exhibit intelligence.”  As patience dwindled so did the funding, and research came to a slow roll for ten years.

So what is in store for the future? In the immediate future, AI language is looking like the next big thing. In fact, it’s already underway. I can’t remember the last time I called a company and directly spoke with a human. These days, machines are even calling me! One could imagine interacting with an expert system in a fluid conversation, or having a conversation in two different languages being translated in real time. We can also expect to see driverless cars on the road in the next twenty years (and that is conservative). In the long term, the goal is general intelligence, that is a machine that surpasses human cognitive abilities in all tasks. This is along the lines of the sentient robot we are used to seeing in movies. To me, it seems inconceivable that this would be accomplished in the next 50 years. Even if the capability is there, the ethical questions would serve as a strong barrier against fruition. When that time comes (but better even before the time comes), we will need to have a serious conversation about machine policy and ethics (ironically both fundamentally human subjects), but for now, we’ll allow AI to steadily improve and run amok in society.

But, how does it work?

This is the history of AI, but how can a computer be able to behave and “think” like a human? Well… I asked ChatGPT to explain to me how AI works in 100 words: here is the result!

AI works by using algorithms to process data, learn from patterns, and make decisions or predictions. It involves training models on large datasets, enabling them to recognize patterns, classify information, or predict outcomes. Techniques like machine learning (where models improve through experience) and deep learning (using neural networks to mimic the human brain) are key components. Once trained, AI systems can perform tasks such as image and speech recognition, natural language processing, and game playing, often surpassing human capabilities in speed and accuracy. AI relies on both supervised learning (using labeled data) and unsupervised learning (finding hidden patterns in data).

ChatGPT

It’s interesting to see how AI segments images to try to understand them like a human would do. IMAGE SEGMENTATION

This is the end : )

This is the end of the first part of this post! This article was about AI history and mechanism. Part 2 will treat AI effect on our planet and its physical form. A really popular topic!

What about you? How often do you think you use AI in everyday life?