Experimenting with ChatGPT reveals concerns

I did not write this.

What follows is an experiment. I wanted to explore the artificial intelligence application called ChatGPT. I gave it instructions to, “Write 800 words in the style of Joe Southern about the pros and cons of Wharton ISD using ChatGPT.” This is the unedited version of what I got:

“Wharton Independent School District (ISD) is a public school district located in Wharton, Texas. As with any educational institution, Wharton ISD is constantly looking for ways to improve and provide the best possible education for its students. One possible solution that Wharton ISD is exploring is the use of artificial intelligence (AI) in the form of ChatGPT, a large language model trained by OpenAI. While there are certainly potential benefits to using ChatGPT, there are also several concerns that need to be addressed.

One potential benefit of using ChatGPT is that it could provide a more personalized and efficient learning experience for students. ChatGPT is designed to understand and respond to natural language, which means that it could potentially serve as a virtual assistant for students who have questions or need help with a particular topic. This could be especially helpful for students who may not feel comfortable asking questions in a traditional classroom setting or who may need additional support outside of regular class hours.

Another potential benefit is that ChatGPT could help teachers and administrators identify patterns in student learning and adjust their teaching methods accordingly. By analyzing student responses to prompts and questions, ChatGPT could provide valuable insights into areas where students are struggling and where additional support is needed. This could help teachers create more effective lesson plans and interventions to support student learning.

However, there are also several concerns that need to be addressed before implementing ChatGPT in Wharton ISD. One of the biggest concerns is the potential for bias in the model. ChatGPT is only as unbiased as the data it is trained on, and there is always a risk that the model could perpetuate existing biases and inequalities. This is especially concerning in the context of education, where biases could impact the learning experiences and outcomes of students from marginalized communities.

Another concern is the potential for ChatGPT to replace human teachers and devalue the important role that teachers play in the classroom. While ChatGPT could certainly serve as a helpful tool for teachers and students, it should not be seen as a replacement for human interaction and support. It is important to remember that education is not just about acquiring knowledge; it is also about developing social and emotional skills, and building relationships with teachers and peers.

Finally, there is also the question of privacy and data security. ChatGPT collects and stores data on the interactions it has with users, which could include sensitive information about students and teachers. It is important to ensure that this data is kept secure and used responsibly, and that students and teachers are fully informed about how their data is being collected and used.

In conclusion, while there are certainly potential benefits to using ChatGPT in Wharton ISD, there are also several concerns that need to be addressed. It is important to carefully consider these pros and cons before making any decisions about implementing this technology in the classroom. Ultimately, the goal of education should be to provide the best possible learning experience for students, and any tools or technologies that can support that goal should be carefully evaluated and implemented with caution.”

For the record, not only isn’t this my style of writing, but it was just 527 words. My big concern about ChatGPT is that it will be used by students to cheat in both doing research and writing essays and other assigned works. I wouldn’t be surprise if it has already happened.

This technology is in its infancy, but it learns and adapts quickly. I bet if I repeat this experiment a year from now I’ll get something very different and alarmingly more accurate. I’ve seen online examples of how OpenAI apps are writing, painting, and doing photo-real images. When you look at this combined with deep-fake technology, it is exciting and frightening to think of the implications this will have.

The ability to hide or manipulate the truth so easily should raise a lot of red flags. The use and abuse of this technology could seriously sway public opinion and policy in alarming directions. It used to be that all a maniacal madman needed to take over the world was an atom bomb. Now all he needs is an app and a devious plot.

OK, maybe things aren’t that dire yet, but it is definitely something to keep an eye on.

Joe Southern is the managing editor of the Wharton Journal-Spectator and the East Bernard Express. He can be reached at news@journal-spectator.com.