A Parent’s Guide to ChatGPT

Every so often, a new technology arrives on the scene that inevitably causes a stir. That’s certainly the case with ChatGPT, an artificial intelligence chatbot capable of some pretty staggering feats. It generates conversational writing that sounds almost human—which is both amazing and alarming, especially for educators, journalists and writers. So, if you have questions about this sleek new tech—and whether it’s safe for children, we have you covered. Here’s what parents need to know about ChatGPT.

What Is ChatGPT and How Does It Work?

ChatGPT is a new artificial intelligence chatbot created by OpenAI. Right now, the team behind the chatbot is still refining the platform, but they’ve released it to the public during their “research preview,” and you can access it for free via the web. In order to explain what the platform is and how it works, we did something novel: we asked the chatbot itself!

Kinzoo: Can you explain ChatGPT in simple terms?

ChatGPT: ChatGPT is a computer program that uses a type of artificial intelligence called deep learning to generate natural-sounding text. It can answer questions, tell stories, and even write poetry. It was trained on a large dataset of text from the internet, so it has a wide range of knowledge and can understand and respond to many different types of inputs.

Kinzoo: And how does ChatGPT work?

ChatGPT: ChatGPT works by using a type of neural network called a transformer, which is trained on a large dataset of text. The network learns to predict the next word in a sentence, given the words that come before it. When given a prompt or input, the model generates text by repeatedly sampling the most likely next word, based on what it has learned during training. The generated text is often coherent, contextually relevant and sometimes even creative.

As you can see, the chatbot responds to user queries, and even answers follow-up questions. People have used the platform to write computer code and even generate college-level essays.

Is ChatGPT safe for kids?

The company behind ChatGPT is transparent about the fact that it’s not a perfect platform. It can sometimes offer misleading information—and make false claims in a very convincing way. We asked ChatGPT about safety concerns as well.

Kinzoo: Is ChatGPT safe for kids?

ChatGPT: As a language model, ChatGPT is a tool that can be used to generate text, it doesn't have any intention or motivation and it doesn't have consciousness. However, ChatGPT is trained on a dataset of text from the internet which includes a wide range of content, including some that may not be appropriate for children. Therefore, it's not recommended for children to interact with ChatGPT without adult supervision. It's always important for adults to monitor and guide children's use of technology to ensure that they are using it safely and responsibly.

Kinzoo: When you say some content might not be appropriate for children, what kind of content are you talking about?

ChatGPT: The text data used to train ChatGPT comes from a variety of sources on the internet, including websites, forums, and social media. This means that the model has been exposed to a wide range of language, including some that may not be appropriate for children. This can include things like profanity, hate speech, and sexually explicit language. Additionally, the model may generate responses or text that could be considered offensive or disturbing. It's important to note that ChatGPT doesn't have a filter that can detect and censor inappropriate content, so it's important for adult supervision to ensure that the content generated by the model is appropriate for children.

What ChatGPT is telling us is that it learned language from the internet. Anything that exists on the internet could, in theory, show up in ChatGPT—including the good, the bad and the ugly. With that in mind, it’s important that children don’t use the platform unsupervised. Adults might need to provide context and intervene in the event that the AI platform produces something disturbing.

What Parents Should Know About ChatGPT

Some teachers and school districts have voiced concern about plagiarism. They’re worried that students could use the platform to complete writing assignments—and pass the work off as their own. And, the concern is real: the New York Times wanted to see if experts could tell the difference between a sample of writing from a student and a sample from ChatGPT. They showed writing samples to a fourth-grade teacher, a professional writing tutor, a Stanford education professor and Judy Blume. Even these experts couldn’t tell every time if they were reading AI-generated writing.

Some school districts are so concerned about cheating that they have banned ChatGPT altogether. Many experts agree, however, that children need to learn how to use this new technology responsibly. It’s a good idea to have a conversation with kids and help them learn what’s appropriate and what isn’t when it comes to AI chatbots.

‍

Editorial credit: Tada Images / Shutterstock.com