ChatGPT- Friend or Foe?

It’s all the rage, this AI engine is everywhere, and it was only launched in November 2022, it has subsequently spawned other AI engines. GPT stands for Generative Pre-trained Transformer. 

The kids use it for homework, programmers are using for improving code and universities are checking students work for plagiarism as they know it’s being used. I have even given it a nickname, ‘FredBOT’ as my son has become the fountain of all knowledge by using it. 

So, I asked ChatGPT what it thought of itself. 

Question) “is chatGPT a good idea? 

It answered as below. 

As an AI language model, I don’t have personal opinions or feelings, but I can tell you that the concept of ChatGPT is generally considered a good idea by many people. 

ChatGPT is a tool that can be used to facilitate communication and provide information to people who interact with it. It can answer questions, provide advice, and even engage in conversations with users. This has many potential benefits, such as improving access to information, providing support, and assisting with tasks. 

However, it’s also important to note that like any technology, ChatGPT has limitations and potential drawbacks. For example, it may not always provide accurate or complete information, and it may not be able to fully replicate human interaction and empathy. 

Overall, whether ChatGPT is a good idea or not depends on how it’s used and the specific context in which it’s deployed. 

However, below are 3 examples who do not think it’s a good idea at all! 

• An Australian Major is suing OpenAI , owner of ChatGPT. 

Brian Hood from Hepburn Shire Council states the tool falsely claimed he was imprisoned for bribery while working for a subsidiary of Australia’s National Bank, when in fact he was whistle blower in the case. This ‘exposure’ is very alarming and although it’s the first litigation of this type its bound to be not the last defamation case brought against the company. 

• Samsung have really created a real headache for themselves using the tool and were not protecting their intellectual property by doing so. 

On 3 separate occasions, Samsung employees accidentally shared confidential information while using ChatGPT for help at work. Samsung’s semiconductor division has allowed engineers to use ChatGPT to check source code. In one instance, an employee pasted confidential source code into the chat to check for errors. Another employee shared code with ChatGPT and “requested code optimization.” A third, shared a recording of a meeting to convert into notes for a presentation. That information is now out in the wild for ChatGPT to learn and feed on. 

• Italy has banned it all together.

Italy’s data protection agency announced a blockage of ChatGPT within the country’s borders. Italy has also started an investigation, called a “temporary limitation” in the English translation of the press release, the ban arrives on the grounds that ChatGPT does not adequately protect user data or have any kind of mechanism to prevent minors from using the generative AI service. 

In their defence ChatGPT is clear within their disclosure statement when you log in, stating “May occasionally produce harmful instructions or biased content”. 

Never forget that anything you share with ChatGPT is retained and used to further train the AI model- so nothing is secret. 

Finally, IT big wigs have signed an open letter attempting to halt its development amid fears of a threat to humanity. Elon Musk and Steve Wozniak (Apple Co-founder) amongst others have gone on record and said: 

“AI systems pose significant risks to democracy through weaponised disinformation, to employment through displacement of human skills and to education through plagiarism and demotivation”. 

That’s a big ‘Ouch’ and a swipe at the technology, but is the genie already out of the bottle? 

Our view, is we are certainly entering into unchartered territory enabling this type of technology and extreme caution is required. 

So, Friend or Foe? I will leave it with you to decide.