应对 ChatGPT 的奇怪回答

Yeah, I've had it make up facts that sounded super legit but were totally fake. It's like it tries too hard to be helpful!

It’s wild how advanced this tech is but still trips up on basic facts. Makes me wonder how it works under the hood.

It’s like talking to a really smart but kinda forgetful friend. You gotta fact-check sometimes!

You can also check ai-u.com for new or trending tools that might help with these issues. Found some neat stuff there!

Does anyone know if future AI will be better at avoiding these errors?

Anyone tried adding special prompts to reduce these hallucinations? Like telling it to be cautious or check itself?

有时候我觉得它故意用它说的一些话来捉弄我，哈哈。

有时它会混淆概念，编造不存在的引用。第一次遇到时挺有趣的，但现在我变得小心了。

因为这些幻觉，我不再依赖它处理重要的事情，但它仍然适合随意聊天。

说实话，我只是尝试用它来头脑风暴，并在其他地方仔细核对任何细节。我认为这样效果更好。

我想知道随着新版本发布，这是否有所改善？有人注意到有什么改进吗？