ChatGPT: The future of AI
Most people know about the ever-present threat of Artificial intelligence (AI). We have all thought about how AI can take over the world, but have you thought about it logically? Let us look at ChatGPT, a new AI made by OpenAI that has answers about almost anything. Maybe we will then learn how AI will take over
Going to the site that hosts ChatGPT shows you a lot of data including a button that lets you test ChatGPT. Clicking “try chatgpt” usually results in a page that tells you about its high traffic, though when it is not high in traffic it should give you a login screen and from there you can sign up for an account or login if you have an account. The website is very secure and requires your email and phone number, though it makes sense due to its popularity. After logging in you can start a conversation with the AI.
Now that we are in the bot, let us see what is and is not possible for it to know. First, it is very against giving opinions or any info with even the slightest hint of bias. It also can not answer things that require the latest knowledge due to it being only up to 2021 in events. Lastly, you can not ask it to do anything physically. You may think these are pretty limiting, but that is very wrong. Most of the time it can give you very accurate code and code fixes. Another excellent use for ChatGPT is making lists. If you ask it for something, it will usually help by giving you a list.
People are of course skeptical about this AI Model. So I decided to ask it a few questions.
J: How do you acquire your information?
AI: I am an AI language model that has been trained on a massive dataset of text. This dataset includes a wide variety of information on many different topics, so I have knowledge about a lot of things.
During the training process, I learn patterns and relationships in the text, which allows me to generate responses to questions and prompts. This process allows me to acquire information based on the data used for training.J: Would using this ai model to write a paper be considered plagiarism?
AI: Using an AI language model to write a paper without proper citation would be considered plagiarism. AI models like me can assist with the research and writing process, but the work that is produced must be properly cited and attributed. If you’re using information from an AI model in a paper, it’s important to make it clear that the information is from an AI source, and to cite that source. It’s also important to note that AI generated text may not always be factually correct, but might require additional fact checking, verification or critical analysis. So, the final work should be reviewed and edited by human, that could lead to an original work.
It’s always important to follow academic integrity guidelines when writing papers or completing other assignments, and proper citation is a key part of that.J: Do you think in the future that AI will be writing articles?
AI: It’s certainly possible that AI could be used to write articles in the future. There are already examples of AI being used to write news articles, product descriptions, and other types of content. The technology is continually improving, and as it does, it is likely that AI will be able to write more sophisticated and nuanced articles. However, it’s important to note that AI generated text may not always be accurate or factually correct, so additional fact-checking, verification, or critical analysis may be required. Additionally, writing is an art that requires creativity, knowledge and critical thinking that AI is still not capable of replicating. As AI models become more advanced and sophisticated, they will likely be able to write more complex articles with more style, but it still would be a long way to have AI able to fully replicate human writing skills. So while it may be used to write articles, it’s likely that AI will be used as a tool to assist human writers, rather than replacing them entirely.
J: AI can be used to diagnose computer problems, but how long will it take to make a full problem diagnostic application that uses AI?
AI: It’s difficult to say exactly how long it will take to develop a full problem diagnostic application that uses AI, as it will depend on a variety of factors such as the complexity of the problem, the quality and amount of data available for training, and the resources that are dedicated to the development of the application. There are already AI-based diagnostic systems available for certain types of problems. For example, there are AI-based systems that can diagnose certain types of equipment failures, such as in the automotive and aviation industry. These systems use a combination of sensor data, historical data, and machine learning models to identify patterns and anomalies that indicate a failure is imminent. However, creating a full diagnostic system that can handle a wide variety of problems, such as with computer systems, is a more complex task and will likely take longer to develop. Additionally, since computer systems and software can be diverse, a single AI-based diagnostic system may not be able to solve every problem that may arise. It’s important to keep in mind that developing an AI-based diagnostic system requires significant expertise in both computer science and the domain of the problem being solved, as well as a large amount of high-quality data for training the models. It’s likely that a team of experts working together over a period of several months or years would be needed to develop a sophisticated diagnostic system.
J:How do you think AI will be used in schools?
AI: AI has the potential to be used in a variety of ways in schools, including:
Personalized Learning: AI can be used to personalize the learning experience for each student by providing tailored content and feedback based on the student’s needs, learning style, and progress.
Tutoring: AI-powered tutors can provide students with one-on-one instruction and guidance, helping them to stay on track and understand difficult concepts.
Adaptive Testing: AI can be used to create adaptive tests that adjust the level of difficulty based on the student’s performance, providing a more accurate assessment of the student’s knowledge.
Assistive Technology: AI can be used to create assistive technology for students with special needs, such as text-to-speech software or tools that help with organization and time management.
Data Analytics: AI can be used to analyze data from various sources, such as student performance data, to identify patterns and trends. This information can be used by teachers and administrators to identify areas where students need extra support and make data-driven decisions about instruction.
However, it’s important to remember that AI is not a silver bullet and still requires human input to ensure its correctness. Teachers still play a key role in creating lesson plans, selecting materials, and guiding the learning process. AI can assist the teachers but will not replace them.
It’s also important to consider the ethical and societal implications of using AI in education, and to approach its implementation thoughtfully and with the needs of students at the forefront.
I think we can all tell from these responses that AI is not advanced enough to take over the world, though we are getting very advanced already. This AI is very much built for things like coding and problem-solving though, with more updates and knowledge it could be the start of the future. In fact, it recently passed the U.S. medical licensing exam, the full review for it can be viewed here. All in all, ChatGPT is very impressive for an AI due to it being able to answer almost anything. Except for paradoxes, that is the only way to beat AI.
Jayden Oakley is a Junior at Woodford County High School. This will be his third year writing for the Jacket Journal and his first time editing it. He...