If you remember chatting with SmarterChild on AOL Instant Messenger back in the day, you know how far ChatGPT and Google Bard have come. But how do these so-called chatbots work, and what is the best way to use them to your advantage?
A chatbot is an AI program that responds to questions as if it were a real human. That seems pretty sophisticated, right? And these bots are. But as it turns out, they do his one thing very well. It’s about predicting words one after another.
Therefore, in the case of ChatGPT or Google Bard, these chatbots are based on so-called large-scale language models. It’s an algorithm that’s basically trained on fill-in-the-blank Mad-Libs style questions. The result is a program that can take user prompts and spit out answers in phrases and sentences.
But what’s important to remember is that although they may look quite human-like, they most definitely aren’t, and they’re just imitating us. They don’t have common sense and aren’t taught the rules of grammar like you and I were in school. Also, they are only as good as what they learned in school – and they can also produce a lot of nonsense.
If you want to learn more about the basics of how chatbots work and the potential dangers (legal or otherwise) of using them, subscribe below. pop science+ Listen to new episodes of as well as read the full story by Charlotte Fu. Please ask me anything.
