1·
1 year agoWhat so many people don’t understand: LLMs like ChatGPT are nothing but statistical engines. They break their incoming text into tokens, and see which tokens usually follow which others. When they generate output, they just roll the dice: After tokens A, B, and C, usually comes a D.
The point is: they have no understanding. If their training data included a good code example, they might regurgitate it. If their training data included broken code, they may regurgitate that. Or they could mix it all together and produce something weird. It’s a lottery, based on what they sucked out of StackOverflow and other places.
This. StackOverflow was great in the early days, when answers were fresh. Now? It’s like so much of the Internet: outdated. Add to that all the students posting their homework problems, and wrong answers by wannabes, well…