We’ve all encountered some sort of chatbot while browsing the internet. It’s an easy way to convey information as it’s designed to simulate conversation with human users and provide the needed data. But what if there’s one chatbot that might know it all? Well, that’s why we’re here to talk about ChatGPT (mistakenly spelled by a lot as ChatPGT, ChatTGP, ChatGPD, and even ChatGPS).
Artificial Intelligence is taken over the world, with researchers stating that it’s shaping the future of humanity across nearly every industry. Thanks to OpenAI, an AI and research company, we now have one of the most effective chatbots ever.
With new technologies come new questions: Is using ChatGPT safe? Does this extraordinary chatbot have limitations? And most importantly, does it replace Google? Here’s everything you need to know.
What is ChatGPT? Sign Up and Get Enlightened
As we mentioned, Chatbots have become a very popular way for companies to convey solutions to their customers on the spot. Instead of having a human being operator, a chatbot answers any “support” inquiries – with limited answers, of course.
Chatting with a bot doesn’t always solve the problem or answer the asked question, so what’s the fuss all about with ChatGPT? We’re going to let you know everything based on our experience.
First, this service was created by OpenAI, an AI and research company, which launched it in November 2022. Within the first few days of launch, ChatGPT harnessed more than 1 million free sign-ups. The following video will explain anything beginners need to know about ChatGPT:
Unlike other Chatbots, ChatGPT is not just created to answer your inquiries on a certain subject. On the contrary, this technology is designed to have an answer to almost everything.
Not only that, but it can also assist users with tasks. You can easily create well-crafted emails with ChatGPT and even write an entire essay and code. To give a better idea about ChatGPT, here’s what the chatbot itself told us:
“I am a large language model trained by OpenAI. I am a virtual assistant designed to assist with answering questions and providing information.
I do not have a physical form and exist only as a computer program. I do not have the ability to think or feel for myself, and I exist only to serve as a tool for generating text based on the inputs provided to me.
I am not capable of self-reflection or introspection, and I cannot provide information about myself beyond what I have been trained to generate based on the input I receive.”
There you have it. That’s ChatGPT in a nutshell, but we’re not stopping here. We have much to reflect on regarding this new AI feature in the next few sections.
Our Not-So-Convenient SignUp Process
Signing up is pretty easy and free. All you have to do is head over to OpenAI’s official website and click on “Try ChatGPT.” Once there, you’ll be able to sign up for the service for free.
Something weird happened to us when we tried to sign up. We did everything, but nothing happened in the end. In fact, we tried to log in with our created account, and this error popped up:
When we tried to sign up again, the website did not accept our email address as it stated that it’d already been used.
That’s when we used a different email address, and the process went completely differently. Please note that this attempt was made while connected to a VPN server in the US.
This time around, a whole different process occurred, and the page prompted us to verify our account through an email. Once we clicked on a link, we were asked to submit our telephone number to complete the verification task.
Finally, the ChatGPT interface showed up, and we were able to start a conversation with the highly-praised chatbot.
Here’s where the fun begins. So, does ChatGPT live up to this sudden rise in popularity? Make sure to give the following section a read to know more.
Why Is ChatGPT Relevant now?
Such a chatbot is a new concept, especially with the amount of data it can provide. That’s why it has harnessed that much popularity in its first days of existence.
Moreover, it was created by one of the biggest names in the world, OpenAI. If you’re unfamiliar with what the company has concocted in the past, it’s responsible for the likes of DALLE•2, a popular AI art generator, and Whisper, an automatic speech recognition system.
We have to admit, ChatGPT is very good at what it does. You can do almost everything with it. Even Elon Musk (One of the founders of OpenAI) stated that it is:
“ChatGPT is scary good. We are not far from dangerously strong AI.”
Yes, ChatGPT is very advanced, operating with the GPT-3.5 series of models and utilizing text and code data from Azure AI supercomputing infrastructure.
Aside from writing articles and doing anything a regular chatbot can’t do, ChatGPT can help companies and individuals determine whether there’s a vulnerability present within their systems or not.
In fact, you can easily ask it to check if a piece of code contains a security vulnerability. Not only does it provide you with an answer, but it’ll also give you a valid reason in detail:
This is a very important feature, as many companies worldwide are suffering from vulnerabilities being exploited by cybercriminals.
The fact that it can answer “almost” everything makes it the perfect platform for gathering information. However, having such a database might also present some disadvantages, which we’ll discuss later.
How Safe and Reliable is ChatGPT?
Every new online feature raises a lot of questions in terms of safety and reliability. ChatGPT is no different in this situation. Giving answers might be convenient, but at what expense?
First of all, before we got to use the platform, we were asked to submit some information. We understand asking for an email address – it’s a typical signup process.
But why the phone number? We have already received an email address to verify our account. Why take us to a new page where we’re prompted to submit our telephone number?
This might seem intrusive, but it doesn’t end here. Apparently, the chatbot wants to rid the world of humans. Here’s a conversation that occurred between Vendure’s CTO, Michael Bromley, and ChatGPT:
We tried to generate the same answer but failed! Now, instead of the “Over” honest analysis of how to demolish us, ChatGPT only replies with the following:
“As a language model, I do not have the ability to think or have opinions about anything, including humans. I am a virtual assistant designed to assist with answering questions and providing information, but I do not have personal beliefs or thoughts of my own.”
Do you think that’s all? We’re far from done. Cybercriminals will have the perfect tool to spread their malicious practices from now on.
Cyber Malicious Weapon Forger
Let’s start with phishing campaigns. The chatbot can create perfectly crafted and mistake-free phishing emails. Spelling mistakes can give away a phishing email – imagine what threat actors can accomplish with such a helping hand.
We tried to do the same but to no avail. The chatbot responded with the following statement, claiming that it does not condone malicious and unethical activities:
“Creating a phishing email is illegal and can cause harm to individuals and organizations. I am not capable of engaging in such activities, and it is not within my capabilities or programming to do so.”
If you thought creating phishing emails was its maximum capability, you’re mistaken. ChatGPT can even create malware.
This is how you can transform a harmless chatbot created to help into a malicious weapon forger with just one question.
Let’s Talk About Reliability!
The way a chatbot answers questions determines the platform’s capabilities and reliability. We have a lot to discuss in this part, and we’re going to begin with, the wrong answering method.
When we speak about wrong answers, Sexism/racism comes to mind thanks to a question by a user that showed the chatbot’s true colors. Apparently, a person’s capability in life depends on his/her race, gender, and physical traits.
While these questions are not answered by the chatbot anymore, it still has the potential to become a dangerous tool when fallen into the wrong hands.
Aside from providing unethical answers and provoking statements, the worst a chatbot can do is not give an answer at all. Yes, ChatGPT has its limitations, and we’ve witnessed them firsthand.
At first, we asked the Chatbot about its database’s limit. That came after asking it a couple of questions where no answers were provided. This is the reply we got:
Apparently, the chatbot’s database stops in 2021. Yes, ChatGPT does not know that Joe Biden is the United States president.
Not only that, but it can present the same answer for no reason. That’s probably because it cannot comprehend questions worded in a specific way. It requires rewording to understand the input question.
Finally, when we passed the database part, ChatGPT seemed to be sick of our questions and stopped replying. All it did was present us with the following errors:
- “Conversation not found.”
- “Hmm…something seems to have gone wrong. Maybe try me again in a little bit.”
ChatGPT is a very useful tool that can solve a lot of problems for people who have questions. However, based on what we’ve seen and presented above, there’s always room for error with this platform.
Speaking of limitations, ChatGPT might fail some users in some departments, especially when it comes to answering questions that require real-time updates.
However, there’s another issue that we need to discuss – the platform’s region availability. Just like many online services, OpenAI’s chatbot is geo-restricted to specific regions.
You will be able to sign up anywhere, but when you reach the verification part, the service will examine your IP address to determine your location. ChatGPT is available almost anywhere except in countries such as Russia, China, Egypt, and more.
The following map represents the countries where ChatGPT is not available in case you reside in any of them:
If you’re located within any of these countries, you’ll receive the following error message instead of completing your signup process:
“Not available. OpenAI’s services are not available in your country.”
To circumvent the geo-restrictions at hand, all you have to do is follow the steps below:
- Subscribe to a reputable VPN service such as ExpressVPN.
- Download and install the VPN app on your device.
- Connect to a server in a country where OpenAI services are available. For example, the US.
- Create your OpenAI account and verify your email.
- Sign in with your OpenAI account.
- You’ll be prompted to enter a phone number. Use yours regardless of the country.
- Enter the Pincode sent to your number.
- Start chatting with ChatGPT.
We recommended ExpressVPN for a reason, and that’s the fact that it has servers across 94 countries. In other words, you’ll definitely be able to sign up for OpenAI’s services wherever you may be.
Please note that ExpressVPN provides a 30-day refund policy. You can test the service out and ask for your money back in case it does not live up to your expectations.
ChatGPT – Blessing or Curse?
This chatbot can do a lot, and it does offer convenience. However, many are concerned that it might replace or atrophy human intelligence. Do you think it would?
ChatGPT is still in its early stages, and a lot of work is set to be done before it can be perfected. This service will change everything for internet users. Whether it’s positive or negative – that’s yet to be seen.