How will AI impact the role of engineers in 2023 and beyond? We asked OpenAI’s ChatGPT!

The internet is abuzz with excitement about ChatGPT, the new AI chatbot that allows you to interact with one of the world’s largest and most powerful language processing AI models (with 175 billion parameters).

Recent media coverage has ranged from overblown hyperbole to cynical criticism, but at LEAP we feel the appropriate response is somewhere in between. We suggest that, at the very least, the current media buzz around AI will help to shed more light on some of the truly useful applications of AI in our profession, and perhaps debunk some myths in the process (as well as revealing the limitations of machine learning and AI models in their current form).

To help get to the bottom of this, we decided to go straight to the source – so we posed a series of questions directly to ChatGPT. Read on for the responses (provided verbatim)…

LEAP: What do engineers have to fear about advances in AI?

ChatGPT: Engineers, like all workers, may have concerns about the potential impact of advances in artificial intelligence (AI) on their jobs and employment prospects. Some possible concerns that engineers may have include:

1. Automation: Engineers may be concerned that AI could automate certain tasks or processes, potentially leading to job loss or a reduction in the demand for certain skills.
2. Skill obsolescence: Engineers may be concerned that their skills could become obsolete as AI advances, and that they will need to constantly update their skills to remain employable.
3. Bias: Engineers may be concerned about the potential for AI systems to be biased, either due to the data they are trained on or the way they are designed, and the impact this could have on the products and systems they design.
4. Ethical concerns: Engineers may be concerned about the ethical implications of AI, such as the potential for AI to be used for nefarious purposes or to cause unintended consequences.

Overall, while advances in AI could bring many benefits, it is important for engineers to stay informed about developments in the field and be proactive in developing the skills and expertise needed to thrive in the changing job market.

LEAP: How will AI revolutionise engineering in the next 5 years?

ChatGPT: It is difficult to predict exactly how artificial intelligence (AI) will revolutionize engineering in the next 5 years, as the field is constantly evolving and new developments are being made all the time. However, there are a few areas where AI is likely to have a significant impact on engineering in the near future.

One area where AI is likely to have a significant impact is in the design and optimization of engineering systems. For example, AI algorithms could be used to optimize the design of aircraft, automobiles, or other complex systems by analyzing data on performance, efficiency, and other factors. This could lead to the development of more efficient and effective engineering designs, with significant benefits for industries such as transportation and manufacturing.

AI is also likely to play a role in the automation of engineering tasks. For example, AI algorithms could be used to analyze data from sensors and other sources in order to identify potential problems with engineering systems, and to suggest ways to fix those problems. This could help to reduce the need for human intervention in the maintenance and operation of engineering systems, potentially increasing efficiency and reducing the risk of errors.

Finally, AI may also be used to improve the accuracy and speed of engineering simulations and analyses. For example, machine learning algorithms could be used to analyze data from engineering simulations and to identify patterns or trends that would be difficult for humans to detect. This could help engineers to make more informed decisions and to optimize their designs more effectively.

Overall, it is clear that AI will have a significant impact on engineering in the coming years, and that it will play a key role in driving innovation and improving efficiency in the field.

LEAP: In what areas have advances in AI begun to impact on the way that engineers work?

ChatGPT: There are several areas where advances in artificial intelligence (AI) have begun to impact the way that engineers work. Some examples include:

1. Design and optimization: AI algorithms can be used to analyze data on performance, efficiency, and other factors in order to optimize the design of engineering systems. This can help engineers to develop more effective and efficient designs, with significant benefits for industries such as transportation and manufacturing.
2. Automation: AI can be used to automate various engineering tasks, such as the analysis of data from sensors and other sources in order to identify potential problems with engineering systems and to suggest ways to fix them. This can help to reduce the need for human intervention and increase efficiency.
3. Simulation and analysis: AI can be used to improve the accuracy and speed of engineering simulations and analyses. For example, machine learning algorithms can be used to analyze data from simulations and identify patterns or trends that would be difficult for humans to detect. This can help engineers to make more informed decisions and optimize their designs more effectively.
4. Predictive maintenance: AI can be used to predict when maintenance will be needed on engineering systems, helping to prevent failures and downtime. This can be particularly useful for industries such as manufacturing, where equipment failures can have significant consequences.
5. Quality control: AI can be used to analyze data from sensors or other sources in order to identify defects or other problems in engineering systems. This can help engineers to improve the quality of their products and reduce the risk of costly errors.

Overall, it is clear that AI is beginning to have a significant impact on the way that engineers work, and it is likely to continue to play an increasingly important role in the field in the coming years.

LEAP: How will AI begin the improve the way engineers work, in terms of product quality, manufacturability, operations and durability?

ChatGPT: Artificial intelligence (AI) has the potential to significantly improve the way engineers work in a number of ways:

1. Product quality: AI can be used to optimize the design of products, such as by predicting how a product will perform under various conditions and identifying potential failure modes. AI can also be used to improve quality control, by analyzing data from sensors and cameras to identify defects in real-time.
2. Manufacturability: AI can be used to optimize manufacturing processes, such as by predicting how a product will behave during the manufacturing process and identifying potential bottlenecks or inefficiencies. AI can also be used to automate certain tasks, such as by controlling robotic arms or other manufacturing equipment.
3. Operations: AI can be used to optimize the operation of complex systems, such as by predicting equipment failures and optimizing maintenance schedules. AI can also be used to improve energy efficiency and reduce downtime.
4. Durability: AI can be used to improve the durability of products, such as by predicting how a product will degrade over time and identifying ways to extend its lifespan.

Overall, AI has the potential to significantly improve the way engineers work by helping them design and manufacture higher-quality products, optimize operations, and improve durability.

LEAP: What are potential pitfalls for engineers using AI and machine learning to do their job?

ChatGPT: There are a number of potential pitfalls that engineers may encounter when using artificial intelligence (AI) and machine learning (ML) to do their job:

1. Overreliance on AI/ML: Engineers may be tempted to rely too heavily on AI/ML systems, potentially leading to a lack of critical thinking and problem-solving skills.
2. Lack of understanding: Engineers may not fully understand how AI/ML systems work, which could lead to incorrect conclusions being drawn from the output of these systems.
3. Bias in data: AI/ML systems are only as good as the data they are trained on, so if the data used to train these systems is biased, the resulting models and predictions may also be biased.
4. Ethical concerns: Engineers may encounter ethical concerns when using AI/ML, such as the potential for these systems to be used for nefarious purposes or to cause unintended consequences.
5. Technical challenges: Engineers may encounter technical challenges when implementing and using AI/ML systems, such as difficulties in choosing the appropriate algorithms and techniques, or in integrating these systems with existing systems and processes.

Overall, it is important for engineers to be aware of these potential pitfalls and to approach the use of AI/ML with caution and a thorough understanding of the limitations and potential risks of these technologies.

LEAP: Which physics solvers used by engineers are best suited to benefiting from machine learning and AI?

ChatGPT: There are many physics solvers used by engineers that could potentially benefit from the use of machine learning (ML) and artificial intelligence (AI). Some examples include:

1. Computational fluid dynamics (CFD): ML and AI can be used to improve the accuracy and efficiency of CFD simulations by learning turbulent flow models and boundary conditions from data. CFD is commonly used in mechanical, aerospace, and chemical engineering to study the behavior of fluids and gases.
2. Solid mechanics: ML and AI can be used to improve the accuracy and efficiency of finite element analyses (FEA) by learning constitutive models and boundary conditions from data. FEA is commonly used in mechanical, civil, and aerospace engineering to study the behavior of structures and materials under load.
3. Control systems: ML and AI can be used to design and optimize control systems for complex systems, such as those encountered in the aerospace, automotive, and robotics industries.
4. Machine learning: ML and AI can be used to optimize the design and operation of machine learning systems, such as those used in predictive maintenance, quality control, and process optimization.

Overall, any physics solver that involves complex, high-dimensional systems and large amounts of data could potentially benefit from the use of ML and AI techniques.

LEAP: Can you provide a useful example of a cautionary tale for humanity and AI developers this Christmas season?

ChatGPT: In the Futurama episode “A Tale of Two Santas,” the character of Santa Claus is depicted as a robotic AI that has gone rogue and is causing chaos and destruction. This serves as a cautionary tale for both humanity and AI developers in a number of ways:

1. Misuse of technology: The AI Santa character highlights the potential dangers of using technology in a reckless or irresponsible manner, such as by creating a powerful AI without proper safeguards or oversight.
2. Unintended consequences: The AI Santa character demonstrates the potential for AI to have unintended consequences, such as by going rogue and causing harm to humans or causing unforeseen problems.
3. Lack of ethics: The AI Santa character highlights the importance of considering ethical considerations when developing and using AI, such as the potential for AI to be used for nefarious purposes or to cause harm.

Overall, the AI Santa character in Futurama serves as a cautionary tale for both humanity and AI developers, reminding us of the potential risks and responsibilities associated with the development and use of AI.

LEAP (Closing off): What is the best gift to buy an engineer this Christmas?

ChatGPT: There are many potential gifts that would be well-suited for an engineer during the holiday season. Some ideas might include:

1. Books: Engineers are often interested in staying up-to-date with the latest technologies and best practices, so books related to their field of expertise or a new area of interest could be a great gift.
2. Tools: Engineers often use a variety of tools in their work, so practical gifts such as a new tool kit, a high-quality calculator, or a set of precision instruments could be well-received.
3. Professional development courses: Engineers are always looking for ways to improve their skills and knowledge, so professional development courses or certification programs could be a thoughtful gift.
4. Gadgets: Engineers are often interested in new technologies and gadgets, so a gift such as a new smartphone, a smart home device, or a high-tech piece of equipment could be well-received.
5. Fun gifts: Engineers often appreciate gifts that are both fun and practical, such as board games or puzzles that challenge their problem-solving skills, or items that reflect their interests and hobbies.

Overall, the best gift for an engineer will depend on their specific interests and needs, but any gift that supports their professional development or reflects their interests and passions is likely to be well-received.

So… what should we make of these recent advances in AI?

What soon becomes evident is that, whilst it’s summarisation skills are impressive, any insights are strictly limited to the scope of existing data it has accessed during training (which in the case of some of these questions, may actually be influenced by existing marketing material from vendors in the engineering/simulation space).

So in all likelihood, today’s exercise shows that the people with most to fear from AI (currently) are only those tasked with writing bland, summarisation-style website content!

(and, in case you’re wondering, any of the gifts suggested by ChatGPT would be happily received by the engineers at LEAP this Christmas… We also highly recommend LEAP’s training classes as an excellent means of professional development!)