It is hard to believe that the launch of the ChatGPT prototype was only in November 2022. If you are not familiar with it, or what it can do, then you need to be. It will have an enormous impact on how we use the Internet and many of the jobs we do now.  ChatGPT and its cohorts will affect us all in ways we cannot begin to imagine.

ChatGPT is an artificial intelligence (AI) chatbot from developer OpenAI Inc. It uses a natural language model to produce human-like text and converse with people. It can already programme PLCs using structured text based on a simple verbal-like instruction. German PLC software engineer Jakob Sagatowski uploaded a 30-minute video to youtube and learnt a lot during the process.

Chat GPT is currently free to try. The newest version GPT4 released in March 2023 is also available to paid subscribers on a limited basis. Comparable products are either under development or launched as prototypes by Amazon, Google, and Microsoft/Bing.

Although the core function of a chatbot AI is to mimic a human conversation, ChatGPT is versatile. For example, it can write and debug computer programs, write business pitches, compose music and poems, paint pictures, and write student essays. It can also answer test questions at a level above the average human test-taker. Yet, to achieve these impressive results, like humans it needs feeding with massive amounts of relevant data.

Chat bots respond to written questions using information from the pre-existing text datasets used to train it, although it can also source information from the Internet. Questions to it can be any length but users must ensure the question is well structured. As in life, poorly structured questions will result in inadequate answers.

Although the dialogue format makes it possible for ChatGPT to answer follow up questions, admit its mistakes, challenge incorrect premises, and reject inappropriate requests.

Since its launch, ChatGPT gained a reputation for its detailed responses and articulate answers across a range of knowledge. However, its irregular accuracy could be a significant drawback. For example, its sources are unknown and unreferenced. Moreover, as it seeks more answers from the Internet, it may lose its moral compass.

WILL CHATGPT AI IMPACT ON INDUSTRIAL AUTOMATION?

Who better to answer that than ChatGPT in the following text:

“As industrial automation continues to advance, engineers in this field must be prepared for the integration of new technologies into their work. One such technology that has emerged as a game-changer in recent years is artificial intelligence, specifically conversational AI  like ChatGPT.

One way that chat bots can benefit industrial automation engineers is by streamlining communication between machines and humans. With its ability to understand natural language, ChatGPT can help engineers quickly identify and troubleshoot issues with machinery, reducing downtime and increasing efficiency. Additionally, ChatGPT can integrate into existing communication platforms, allowing for seamless communication between humans and machines.

Another way that ChatGPT can benefit industrial automation engineers is by aiding in decision-making. As data collection and analysis become increasingly important in this field, ChatGPT can assist in interpreting large amounts of data and making predictions based on that data. This can help engineers make more informed decisions about maintenance schedules, inventory management, and production planning.

However, there are also potential challenges that engineers must consider when incorporating ChatGPT into their work. One major concern is the potential for job displacement, as ChatGPT and other AI technologies may replace certain roles previously taken by humans. Additionally, there is the issue of data privacy and security, as ChatGPT must be trained on large amounts of data, which could potentially include sensitive information.”

We are in the initial stages of AI assistants and chat bots. As they gather knowledge and move into the leading search engines, they will enhance knowledge. The use case will change as we become familiar with their strength and weaknesses. It will also be interesting to see whether organizations and individuals feel the need to ringfence their information.