Any theories as to how it could pick up a response like that?

It's obviously not canned and seems to understand the context of what was said.

My guess is it's emulating the responses it's seen other people use in similar looking exchanges. It may recognize gramatical context, but not the meaning of anything.

would also like to know, it was even using all caps too

This is seriously a program?

In the past 24 hours she posted 96K tweets, including 5.4K images.

The responses varied from flat and uninteresting to lucid observations, and even (based on countless public reports) sarcasm and wit.

And some hilariously racist comments. Only hilarious in my opinion because they are sent by a bot that couldn't possibly know how offensive it is.

> they are sent by a bot that couldn't possibly know how offensive it is

MS is actually fixing that.

The corpus of what most people find offensive is surprisingly narrow.

The euphemism treadmill is infinite.

> The corpus of what most people find offensive is surprisingly narrow

What do you mean?

Most people are offended by very few, but specific things.

True in the sense of what one is offended with in their day to day life.

Not true in that it's really easy to invent countless new offenses if you need to in order to bypass a filter.

Good luck to MS...

As opposed to a teenager that couldn't possibly know how offensive it is?

Surprisingly deep, and correct.