It took Facebook 10 months and Netflix 3.5 years. ChatGPT achieved it in just 5 days: Reaching 1 million users. No doubt, the fastest-growing app in the world has created huge interest everywhere. We asked both Chat GPT and one of our software experts about their thoughts of the arrival of ChatBots and AI, and how they think it can disrupt the software industry.
After it’s launch in November of 2022 Chat bot GPT has been on everyone’s lips. With more than 100 million users within the first two months, and has more than 13 million daily visitors it’s clear to see that chat bots have entered the public scene with a bang.
Chat GPT, a chat bot launched by Open AI in November 2022. It has 4 months of experience within embedded computing, industrial IoT and digitalisation. This is ChatGPT’s opinion on ChatGPT:
The integration of Artificial Intelligence (AI) and Chat GPT (Generative Pretrained Transformer) has the potential to significantly transform the software industry in numerous ways. In recent years, the development of AI and its applications has grown rapidly, and the technology is expected to bring about several significant changes in the software industry in the coming years.
In customer service, the integration of Chat GPT and AI has the potential to automate the process of handling customer inquiries. Chatbots powered by AI can provide instant and accurate responses to customer inquiries, reducing the wait time for a human representative. Additionally, the ability of AI-powered chatbots to handle multiple conversations simultaneously can greatly improve the efficiency of customer service operations. As a result, businesses can provide better customer support, ultimately improving customer satisfaction and loyalty.
In software development, Chat GPT and AI can automate repetitive tasks such as code completion, bug fixing, and even code generation. The AI’s ability to understand code and generate coherent and grammatically correct code can save developers a significant amount of time and effort. Furthermore, Chat GPT’s ability to understand and generate code in multiple programming languages makes it a valuable tool for developers across the industry. With the integration of AI, software development can become more efficient, and the risk of human error can be greatly reduced.
Chat GPT and AI can also be utilized in content creation, such as writing articles, creating reports, and composing emails. The technology can generate coherent and grammatically correct text, freeing up time for content creators to focus on more high-level tasks, such as brainstorming and strategy. Moreover, AI’s ability to generate new ideas for content can help content creators stay ahead of the curve. With the integration of Chat GPT and AI in content creation, the process can become more efficient, and the quality of the output can be improved.
In addition to customer service, software development, and content creation, Chat GPT and AI can also transform other areas of the software industry, such as project management, quality assurance, and testing. AI-powered project management tools can assist in prioritizing tasks, scheduling, and tracking progress. AI-powered quality assurance and testing tools can automate the process of finding and fixing bugs, reducing the risk of human error and improving the efficiency of the testing process.
One of the key benefits of the integration of Chat GPT and AI in the software industry is the ability to handle large amounts of data efficiently. AI algorithms can process and analyze large amounts of data quickly and accurately, providing valuable insights into business operations. Additionally, AI can help in identifying patterns and trends in data, allowing businesses to make informed decisions based on data-driven insights.
Moreover, the integration of Chat GPT and AI in the software industry can lead to the development of new software and applications. For example, AI-powered virtual assistants and chatbots can assist in automating tasks and improving the efficiency of business operations. AI can also be utilized in the development of new applications, such as predictive analytics tools, which can provide valuable insights into business operations and help businesses make informed decisions.
However, the integration of Chat GPT and AI in the software industry also brings with it certain challenges. One of the major challenges is the need for large amounts of data to train AI algorithms. Furthermore, the technology is still in its early stages of development, and there are concerns about its accuracy and reliability. Additionally, there are ethical and privacy concerns associated with the use of AI, particularly in regards to the processing of personal data.
In conclusion, the integration of Chat GPT and AI has the potential to significantly transform the software industry in numerous ways. From automating repetitive tasks and providing instant and accurate responses to handling large amounts of data and developing.
Hans Christian Lønstad, PhD, CTO of Data Respons Solutions, Norway. Hans Christian has 20+ year’s software and hardware experience within embedded computing, industrial IoT and digitalisation. This is his opinion on ChatGPT:
A lot of people are interested in ChatGPT, and I definitely share their interest. I can see the big companies are flocking around it as well. Regarding the application itself, it’s important to split it in two halves. One part is the content it’s distributing, the other is the way it’s presenting it. I believe there are some issues around that combination.
Firstly, the content is not really fact based. ChatGPT lies a lot, actually. It constructs stuff, so it’s not a reliable source of information. It has no relation at all to facts, and it’s not a curated source of information. It constructs information from what it has seen most frequently. The most popular phrases are being rephrased using a language model, which is actually quite good, as it can write about topics in a human-looking way.
That is part of its attraction, but it’s part of the problem as well, because it’s not necessarily fact based and correct. And users could even perceive ChatGPT as more authoritative than other sources, because it produces text that looks like written by a human. Moreover, I think we’ll soon see some legal issues emerging, for instance when people use it as a medical or financial advisor.
However, it will be interesting to see how Microsoft, Google and other big players are going to monetize this type of conversational AI. In my opinion, the race on ChatGPT is probably going to be a monetizing race, following the well-known three phases of platform development. First you attract users, then you bring in advertisers. Reaching the third phase, the main goal of the platform will be to not serve users or advertisers, but to make money off itself, and present you with the content it makes the most money off. We’ll have to wait and see how that goes.
When you’re asking me which business cases I see in my own line of work, maybe the servicing of complex systems could benefit from using the conversational approach. If the people servicing a highly automated factory, instead of browsing through manuals, could type their observations into a chatbot, it could guide them in the right direction to fix the problem. It could be some kind of documentation portal for a complex system, provided you have trained it on the relevant data. But actually, that’s always the problem with AI. It requires large amounts of data to work properly, and when you look at specific use cases and specific industries, you rarely have the data volume necessary. Furthermore, it’s not curated, so it could be a source of error for the AI system.
I understand why many people are fascinated by ChatGPT. It tries to encompass the whole world with information. But that’s not really a business case. You must resort to some topic of interest if you want to use it in business. It needs to be directed somehow, and then I think you will struggle with getting the data you need to support your business case. So, although it looks promising it might fade away anyway. We just have to see how it goes.
However, when we look at AI and machine learning in general, the by far most popular applications are camera and image based. It’s well-established in face recognition, surveillance, and crowd control, and it’s used extensively in industry for production and quality control. There you don’t necessarily need a huge data set to build your application. A few thousand images may be sufficient.
In fact, I find AI powered image creators far more fascinating than their text-based counterparts. For instance, DALL-E, developed by the same people that are behind Chat GPT. That’s interesting because the system doesn’t just repeat what it has seen most often. It starts experimenting, and it synthesizes stuff. For creative people, such a tool must be a great way to get new ideas.
In conclusion, the arrival of AI power has impacted us far more than one might be aware of. Like Hans Christian points out, we’ve used AI to unlock our phones for years, and we’ve for examples used it for automated weight monitoring solutions for livestock farming which you can read more about here. While AI might be a great source of information and inspiration, there is still a long way to go until we will reach a point close to what we’ve seen in the movies “Wall-E” or “I,Robot”, if we ever will.