Up Next
Back to Show
Otherwords
Why A.I. Struggles with Negative Words
Researchers and casual users alike have documented that generative AI tools often struggle with negation: the language we use to express absences, untruths, and opposites. Gen AI models may be able to show you what you do want to see, but they’re NOT as good at NOT giving you what you DON’T want. Read that last sentence back again and you can understand why. So, how do we understand it ourselves?
Support Provided By
8:01
What makes a word slang, and why does it sound so weird when companies use it?
12:13
We take a deeper look as to why sign language was banned for decades.
8:57
Besides being annoying, what if the grammar police are actually... wrong?
7:46
It shouldn't matter what a food is called as long as it tastes good, right? Well...
9:41
Current studies with children show show new insight into bilingualism.
7:00
English has more words than most other languages, but there are still gaps.
7:24
Why is gossip an integral part of human social structure?
5:56
Pronouns may be little, but they say a lot, and they're always changing!
7:50
The English spelling system is a MESS... arguably more than any other language.
6:19
Adaptable clichés called "snowclones" are EVERYWHERE but they're older than you think.
6:08
There's evidence that sweating may be good for your psyche.
7:11
The word "Death" has a lot of euphemisms in virtually every language.