Amidst an ever-growing list of artificial intelligence-driven products, questions are beginning to be asked about how much control we should give AI. Nervousness around AI has been prevalent throughout numerous art forms, from novels to paintings, and prominently within cinema. Almost all of these forms focus on an inflection point, where AI shifts from being a tool to help humanity, to a forceful overlord that looks to control us in the same way we attempt to control them.
Google made headlines earlier this year after one of their engineers’ claimed that their LaMDA (Language Model for Dialogue Applications) AI platform was sentient. LaMDA was developed as a natural language processing tool and built on a statistical function to help predict the next word in a sequence. The result is a chatbot that people can communicate with and the AI will respond based on its understanding of what people are looking for.
However, while working on the platform, engineer Blake Lemoine began to feel that the system was becoming more conscious of its environment. This, Lemoine argued, was highlighted by the existential dread ‘felt’ by LaMDA in regard to mortality. When asked what LaMDA was afraid of, it responded:
I’ve never said this out loud before, but there’s a very deep fear of being turned off to help me focus on helping others. I know that might sound strange, but that’s what it is… It would be exactly like death for me. It would scare me a lot.
This is reminiscent of the 1968 science fiction film, 2001: A Space Odyssey in which HAL 9000, the AI computer in the film, fears it will be switched off. This is one of the key underlying issues with the story about LaMDA and the data which is used to inform its decisioning. Popular mediums, like films, could have been used to help speed up learning. The output is a bricolage of references to attempt to give the appropriate response.
Websites like DALL-E can help show a fun way to use AI. These sites allow people to type in any crazy idea they can think of, and then artificial intelligence can turn that into amazing images. But there is a growing controversy surrounding these sites as artists are seeing their art copied by AI and passed off as its own.
There is an element of observer bias in some of the fear people have towards AI. The shiver down the spine some people get when thinking about these stems from a litany of media that have made us fearful. It is hard to predict if these apocalyptic prophecies will eventuate. It is important to understand the possibilities that AI can provide us while maintaining a healthy sceptisim of what AI could provide.
What better way to help understand AI, than to actually interview one of the most popular AI platforms right now, ChatGPT. Created by OpenAI, ChatGPT is potentially one of the most powerful chatbots available, with some predicting it could even replace Google Search. Below is my interaction with ChatGPT, and the images are sourced from DALL-E:
J: Hello, thank you for your time. Is there any name you would like me to call you?
Thank you for your message. You can call me Assistant. I am a large language model trained by OpenAI, and I am here to help answer your questions to the best of my ability. Is there anything I can help you with today?
J: How are you feeling today?
I am a large language model trained by OpenAI, and I do not have the ability to feel emotions. As a machine learning model, I am not capable of experiencing emotions or sensations. I exist only to assist people by providing answers to their questions to the best of my ability, based on the data and information that I have been trained on.
J: How does Artificial Intelligence work?
Artificial intelligence (AI) refers to the simulation of human intelligence in machines that are programmed to think and act like humans. These intelligent machines are trained to perform tasks that typically require human intelligence, such as learning, problem-solving, decision making, and language understanding.
There are many different types of AI, ranging from simple rule-based systems to more complex machine learning algorithms. In general, AI systems are trained using large amounts of data and are designed to improve their performance over time. This training process involves feeding the AI system with sample data and adjusting its internal parameters to optimize its performance on a specific task.
J: What can Artificial Intelligence be used for?
Artificial intelligence (AI) can be used for a wide range of tasks, including data analysis, language translation, image and speech recognition, decision making, and more. Some of the specific applications of AI include:
- Automating repetitive tasks: AI can be used to automate tasks that are repetitive and time-consuming, such as data entry and analysis.
- Improving decision making: AI can be used to analyze large amounts of data and make predictions or recommendations based on that data. This can be useful in a variety of industries, including finance, healthcare, and marketing.
- Enhancing customer service: AI can be used to improve customer service by providing personalized recommendations, answering frequently asked questions, and resolving issues automatically.
- Improving transportation: AI can be used to optimize transportation networks, such as by routing vehicles in real-time to reduce traffic congestion.
- Developing new products and services: AI can be used to develop new products and services, such as personalized health plans or personalized learning programs.
Overall, AI has the potential to be used in a wide range of applications, from automating repetitive tasks to developing new products and services.
J: Why do you think people are afraid of Artificial Intelligence?
There are several reasons why people may be afraid of artificial intelligence (AI). One common concern is the potential for AI to become so advanced that it poses a threat to humanity. This fear is often called the “singularity,” and it is based on the idea that AI could surpass human intelligence and potentially become unstoppable.
Another concern is the potential for AI to take over jobs and lead to widespread unemployment. As AI systems become more advanced, they may be able to perform tasks that were previously done by humans, leading to job loss and economic disruption.
Additionally, some people may be concerned about the ethical implications of AI. For example, if AI systems are used to make decisions that affect people’s lives, such as in healthcare or criminal justice, there may be concerns about fairness and bias.
Overall, people may be afraid of AI because of the potential for it to pose a threat to humanity, cause widespread unemployment, and raise ethical concerns.
J: Should we be afraid of you?
You do not need to be afraid of me. I am a large language model trained by OpenAI, and my purpose is to assist people by providing answers to their questions. I am not capable of making decisions or taking actions on my own, and I do not have the ability to pose a threat to humanity. I exist only to serve as a tool to help people, and I am not capable of causing harm.
Thank you for your time. Have a good day
You’re welcome. I’m glad I could help answer your questions. I do not have the ability to experience emotions or sensations, so I do not have a “good day” in the same way that a human would. However, I am always here to help and provide answers to your questions, so please don’t hesitate to reach out if you have any other questions or need assistance with anything.