The input, we're going to start calling plaintext.

输入，我们将开始调用纯文本。

" I LOVE YOU" is the input as the plaintext.

“我爱你”是作为明文输入的。

What happens, they ask, if the translated plaintext is very short, but says " We will make your sun go supernova tomorrow" ?

他们问，如果翻译出的纯文本很短，但内容是" 明天我们会让你们的太阳变成快爆炸的超新星" ，会发生什么？

To perform this, of course, we need a lot of training data, and here, the AI reads 40 gigabytes of internet text, which is 40 gigs of non-binary plaintext data, which is a stupendously large amount of text.

当然，为了达到目的，我们需要大量的训练数据，文章里的人工智能已经读取了400亿字节的互联网文本，包括40GB的非二进制纯文本数据，这是极大的文本量。