Is Artificial Intelligence taking over the world?
Everything you need to know about ChatGPT, the AI tool that's making waves.
Key points
- ChatGPT is a commercial product released late last year using ChatBot programming.
- ChatGPT can understand and generate text in a human-like manner, answering questions, providing information, and generating creative writing.
- There are fears it will be used to spread disinformation.
We have read it is going to ruin education as we know it, make humans redundant, threaten millions of jobs, and refashion art and creativityy.
It’s the latest tech sensation, developed by a San Francisco-based company called OpenAI – but what exactly is ChatGPT?
So, we got on a laptop computer, opened the ChatGPT app, and asked it: “In simple terms, what is ChatGPT?”
It replied: “ChatGPT is an advanced AI language model developed by OpenAI that is specifically designed for conversational purposes.
“It can understand and generate text in a human-like manner, answering questions, providing information, generating creative writing, and more.
“It works by using machine learning algorithms to analyze and understand patterns in vast amounts of text data and can then generate new text based on that understanding.
“The goal of ChatGPT is to enable more natural and human-like interactions between people and AI.”
ChatGPT can “talk” about a wide range of topics, generate song lyrics and suggest edits to computer programming code.
It learns to mimic the grammar and structure of human writing and reflects frequently used phrases.
However, the chatbot is not always accurate. Its sources are not fact-checked, and it relies on human feedback to improve its accuracy.
For our next experiment, we typed into ChatGPT: “Write a poem praising older Australians.”
We didn’t expect much, but in about five seconds, here is what it produced:
A poem praising older Australians
Older Australians, a treasure trove of knowledge,
Their lives filled with stories and wisdom that college
Can’t teach, with memories that go back so far,
Of days when life was simple, yet still full of heart.
Their laughter is warm, their spirit is bright,
And the twinkle in their eyes can light up any night.
Their love for their country shines through and through,
And their kindness and grace are simply true.
Their hard work and determination, an inspiration,
Their journey through life, a cause for admiration.
From building a nation to raising a family,
Their contributions to society, immeasurable, truly.
So, here is to the older Australians, this we say,
We celebrate you and your wisdom every day.
You’re the backbone of our nation, a source of pride,
And we’re grateful for all that you bring to our side.
Did you know?
- ChatGPT was launched as free to the public, with plans for a premium version of the service, called ChatGPT Plus, for $20 per month. There will still be a free version that people can use during off-peak times.
Why has ChatGPT hit the headlines, even though it was launched just a few months ago?
Well, because people are using it in their millions – and they are getting replies that can be human-like, wise and witty, but also problematic or just plain wrong.
Users are having a lot of fun working out what ChatGPT and similar programs can do.
Threats, misuse and disinformation
OpenAI says it recognises the dangers and is collaborating with universities to investigate how it might be misused for disinformation purposes. After more than a year of research, a report was written outlining the danger if used to augment disinformation campaigns. Just what we need, more disinformation from politicians, influencers, and so-called experts.
The report writers concluded: “We believe that it is critical to analyse the threat of AI-enabled influence operations and outline steps that can be taken before language models are used for influence operations at scale. We hope our research will inform policymakers new to the AI or disinformation fields and spur in-depth research into potential mitigation strategies for AI developers, policymakers, and disinformation researchers.”
According to the Washington Post – it is being used to write songs, movie and TV scripts, computer programming language, social media, and potentially plagiarise school and university essays.
Watch out, journalists! The Washington Post writer said that when he asked the chatbot to write a headline for his article, it returned three suggestions:
- “GPT-3 chatbot revolutionises the way we communicate with AI.”
- “Meet the GPT-3 chatbot: the smartest AI on the planet.”
- “GPT-3 chatbot leaves humans in the dust with its advanced conversational abilities.”
Hmmm! That last option is a bit of a worry, especially if you have seen the Matrix movies. Even more so, if you read it together with this disarming ChatGPT self-analysis: “As a machine learning model, I do not have feelings”, the model’s answer will tell you if you ask how it is feeling. “I am designed to process and generate text based on the inputs I receive."
Can we be sure about that?
For further reading: OpenAI, Washington Post and The New York Times
