BY ZANA RAYBON, FBPE EXECUTIVE DIRECTOR & FEMC PRESIDENT
Most of you have probably been hearing a lot of chatter about AI (artificial intelligence) and how it is taking over our world. That might be an exaggeration but, in reality, it has been at the forefront of the news for the past few months.
I decided to give it a try. It is truly a wonderful tool for so many web users. In fact, one of our staffers came across an article about 20 entertaining uses of ChatGPT you never knew were possible. Things like writing a novel, creating games, dealing with loneliness and anxiety, and even gift ideas. You can ask ChatGPT anything.
I asked it: “How do I explain ChatGPT to engineers?” Here is what it told me:
As an AI language model, ChatGPT is a system that uses natural language processing and machine learning to generate human-like responses to user inputs. It is trained on a large corpus of text data and is designed to respond to a wide range of prompts and questions.
To explain ChatGPT to engineers, you could describe the underlying technology and architecture of the system. This might include discussing how the model was trained, what data was used to train it, and what algorithms and techniques were employed to optimize its performance.
You could also explain the different components of the system, such as the input and output layers, the hidden layers, and the activation functions. Additionally, you could discuss the ways in which ChatGPT is used in various applications, such as chatbots, customer service, and virtual assistants.
Overall, the key to explaining ChatGPT to engineers is to focus on the technical details of how the system works and the different ways in which it can be applied to solve various problems.
I also tried DALL·E 2, which is an AI system that can create images and art from a description in natural language.
The image at right is one created for me when I asked DALL-E to “explain engineering to kids using a cartoon.”
Next, I asked ChatGPT: “How can AI change engineering?” This is the response I got:
Artificial intelligence (AI) has the potential to revolutionize many aspects of engineering, including design, analysis, manufacturing, and maintenance. Here are some ways that AI can change engineering:
- Design optimization: AI can be used to optimize designs, taking into account multiple factors such as performance, weight, and cost. By using machine learning algorithms to analyze vast amounts of data, engineers can identify the most efficient designs and reduce the time and resources required for testing.
- Predictive maintenance: AI can be used to monitor the health of equipment and predict when maintenance is needed. This can help to reduce downtime and prevent costly equipment failures.
- Quality control: AI can be used to detect defects in products and identify the root causes of quality issues. This can help to improve the reliability and consistency of manufactured products.
- Energy efficiency: AI can be used to optimize energy consumption in manufacturing processes, as well as in building systems. This can help to reduce energy costs and improve sustainability.
- Autonomous systems: AI can be used to develop autonomous systems, such as self-driving cars and drones, that can operate without human intervention. This has the potential to revolutionize transportation and logistics.
Overall, AI has the potential to improve efficiency, reduce costs, and enhance the performance and reliability of engineering systems. However, it is important for engineers to understand the capabilities and limitations of AI and to work collaboratively with AI systems to ensure safe and effective operation.
Finally, I asked DALL-E to produce a “Matisse-style painting of engineering plans” and the image at right is one of four it created.
Like it or not, AI is here. We might as well find some good uses for it. Try it for yourself and see what you think!