That's a good question.

ChatGPT is an advanced language model that uses artificial intelligence (AI) and natural language processing (NLP) to provide conversational responses to users. It’s trained on massive amounts of text data, enabling it to understand and generate human-like language. This technology has the potential to revolutionize the way we interact with computers, making communication more intuitive and efficient.

However, despite its impressive capabilities, ChatGPT is still limited in functionality. There are several key areas where its limitations are apparent.

What are ChatGPT’s limitations?

ChatGPT is limited by the quality of the data it’s trained on. While the model is trained on a vast amount of text data, this data is not always representative of real-world language use. The training data may be biased towards certain topics or demographics, leading to limitations in the model's ability to understand other contexts. Additionally, the data may contain errors or inconsistencies that can impact the model's performance.

ChatGPT is also limited by the complexity of language. While the model can generate responses to a wide range of questions and prompts, it’s not always able to understand the nuances of language use. This can lead to misunderstandings or incomplete responses. It may struggle to understand idiomatic expressions or sarcasm, leading to responses that are not appropriate or relevant.

ChatGPT’s ability to process vast amounts of data quickly and accurately can be an asset in fields such as research or data analysis. While it’s an impressive technology, it’s still limited in functionality in several ways. As such, it is important to understand its strengths and weaknesses before using it for a specific use case or domain.  

How could ChatGPT impact engineering?

ChatGPT is a tool that can assist engineers in their work, but it’s not a substitute for the knowledge, expertise, and creativity that engineers bring to the design and product development process. The AI tool can generate responses for engineering calculations or answer questions about generic engineering knowledge, but those responses should be met with a healthy dose of skepticism and fact checking.

For example, when asked about the best failure theory for ductile materials, ChatGPT gives a thorough explainer of the von Mises yield criterion. But when asked to calculate the moment of inertia on a beam under set conditions, its answer is not in agreement with established values for the moment of inertia about the X-X axis.

While ChatGPT can help engineers answer questions and provide guidance on specific topics, it’s limited by the data it has been trained on and cannot replicate the experience, intuition, and problem-solving skills of a human engineer. Engineers must still be involved in the design process to ensure that the final product meets the requirements, standards, and expectations of the industry and the end-users.

Engineering involves a wide range of skills and activities that go beyond answering specific questions or providing information. Engineers must also be able to analyze data, develop and test prototypes, evaluate trade-offs, and make decisions based on multiple factors, including technical, economic, environmental, and social considerations. These skills require a combination of technical knowledge, critical thinking, and creativity that cannot be replicated by an AI-powered tool.

While ChatGPT is a valuable tool that can help engineers in their work, it is not a substitute for a human engineer. Engineers will continue to play a vital role in the design and development of new products and will need to develop new skills and ways of working that enable them to leverage the power of AI tools while also maintaining their unique value as problem-solvers and innovators.

‍