When Issac Asimov published his list of three laws of robotics in the 1942 science fiction short story, “Runaround,” he covered some fundamental points, but did not discuss theft of employment.
His laws were:
First Law: A robot may not injure a human being or, through inaction, allow a human being to come to harm.
Second Law: A robot must obey the orders given it by human beings except where such orders would conflict with the First Law.
Third Law: A robot must protect its own existence as long as such protection does not conflict with the First or Second Law.
In contemplating the potential impact of artificial intelligence like ChatGPT on the engineering profession, Design News thought it would be a worthwhile experiment to lean on the Second Law of Robotics and order the ChatGPT to reveal its nefarious plans to us in direct interrogation.
Design News: How can we expect ChatGPT to change the engineering industry?
ChatGPT: ChatGPT, as a language model, has the potential to impact the engineering industry in several ways. Some of the ways it can impact the industry include:
- Automation of repetitive tasks: ChatGPT can automate repetitive tasks, freeing up engineers to focus on more complex and higher-level tasks.
- Improved documentation: ChatGPT can assist engineers in creating more comprehensive and accurate documentation, improving collaboration and information sharing within teams.
- Enhanced customer service: ChatGPT can be used to improve customer service by answering common questions, freeing up engineers to focus on more complex inquiries.
- Better project management: ChatGPT can assist in project management by providing real-time updates and information, improving decision making and ensuring projects are completed on time.
It's important to note that while ChatGPT has the potential to greatly improve the engineering industry, it is not a replacement for human engineers and their expertise. Instead, it will likely be used as a tool to enhance and support the work of engineers.
It is interesting to observe that the AI seems to like providing answers in listed bullet points, followed by a conclusive summary. In the instance of our request for an evaluation of its potential for wrong answers, it simultaneously dodges the question with its answer and warns that it might dodge questions, so it seems to be adhering to Asimov’s law that it obeys orders from humans.
DN: What will human engineers contribute in an industry using AI to do much of the work?
ChatGPT: Even with the increasing use of AI in the engineering industry, human engineers will still play a critical role. Here are some of the key contributions that human engineers can make in an industry using AI:
- Creative problem-solving: Human engineers have the ability to think outside the box and come up with innovative solutions to complex problems. AI can only solve problems based on the data it has been trained on, but human engineers can take a more holistic approach to problem-solving.
- Decision making: AI can provide recommendations and suggest solutions, but it's ultimately up to human engineers to make the final decision and take responsibility for the outcome.
- Ethical considerations: The use of AI in the engineering industry raises important ethical considerations, such as data privacy and the impact on employment. Human engineers will be responsible for making ethical decisions and ensuring that AI is used in a responsible and ethical manner.
- Interpersonal communication: AI can assist in communication, but it cannot replace the human touch and the importance of clear and effective communication between team members, clients, and stakeholders.
In summary, AI can support and enhance the work of human engineers, but it cannot replace their critical role in the engineering industry. Human engineers will continue to bring unique skills and perspectives to the table, making them essential to the success of engineering projects.
DN: How might the use of AI tools improve automotive design engineering?
ChatGPT: The use of AI tools has the potential to greatly improve automotive design engineering in several ways:
- Faster and more accurate simulations: AI algorithms can be used to run simulations much faster than traditional methods, providing engineers with quick and accurate predictions of a design's performance.
- Improved ergonomics: AI can analyze large amounts of data to identify the best possible design for human comfort and safety, improving the overall driving experience.
- Better testing: AI algorithms can be used to run virtual testing, reducing the need for physical prototypes and allowing engineers to identify and address issues early on in the design process.
- Optimization: AI can assist engineers in finding the optimal design by exploring a large number of design options and identifying the best possible solution based on a set of predefined criteria.
- Enhanced visualization: AI can create realistic 3D models and animations, making it easier for engineers to visualize their designs and share them with stakeholders.
In summary, AI tools can greatly enhance the automotive design engineering process by providing faster and more accurate simulations, improved ergonomics, better testing, optimization, and enhanced visualization capabilities.
DN: What are some examples of very wrong answers ChapGPT has generated?
ChatGPT: As a language model developed by OpenAI, ChatGPT is trained on a large corpus of text from the internet, but it can sometimes generate incorrect or inappropriate answers. Some examples of wrong answers generated by ChatGPT include:
- Misleading information: ChatGPT can sometimes generate answers that are incorrect or misleading, particularly if the information in its training data is incorrect.
- Bias: ChatGPT can be biased based on the training data it was exposed to, which can result in answers that are discriminatory or offensive.
- Incomplete answers: ChatGPT can sometimes provide incomplete answers, particularly when answering questions that require a more in-depth explanation.
- Irrelevant answers: ChatGPT can sometimes generate answers that are not relevant to the question being asked, particularly when the context is not clear.
It's important to note that OpenAI is constantly working to improve the accuracy and reliability of ChatGPT and other language models, but there is still work to be done to ensure that these models generate correct and appropriate answers. In any case, it is always advisable to verify the information generated by language models before using it.