Like an AI Could Ever Spot Sarcasm • Hacker News Board

Re: Like an AI Could Ever Spot Sarcasm

#21

Post by Stratoscope » Wed, Jan 31, 2018, 11:17 PM UTC

com2kid wrote: post #18

Stratoscope wrote: post #8

Like a human being could ever read that text. If you're having as much trouble reading it as I was, open the developer tools and on the body style, remove "DINPro" from the font-family, turn off the font-weight: 300 or change it to 400, and increase the font-size to 16px or whatever size you like. If the AIs ever do take over, my one request is that they use plenty of sarcasm when they talk about designers who think…

It actually looks quite nice in Firefox, it is hard to read in Chrome though. Maybe they have the one last web design team that primarily tests in FF? :D

I'm curious which OS you're using. On Windows, it looks pretty much equally bad to my eyes in Chrome, Firefox, and Edge.

Re: Like an AI Could Ever Spot Sarcasm

#22

Post by ACow_Adonis » Wed, Jan 31, 2018, 11:25 PM UTC

To be perfectly fair, human beings can't pick up on sarcasm reliably: or at the very least it seems to be cultural/contextual.

Australians/brits consistently bemoan the inability of Americans to understand deadpan and sarcasm.

And I'm even reminded of one of my European friends (from Austria) bemoaning conversations with Germans along the lines of:

Austrian: "could you be any more condescending!?" German: "yes I could be more condescending."...blank stare.

Re: Like an AI Could Ever Spot Sarcasm

#23

Post by ACow_Adonis » Wed, Jan 31, 2018, 11:30 PM UTC

JoeAltmaier wrote: post #12

It's more than incongruity. Context is king. "I like being ignored" is sarcasm. But followed up with "No, really, I like being ignored. Its like a super power! I can ..." is serious (sort of).

And then you get people like me, where "I like being ignored" is not sarcasm, but a commentary/personality preference related to disliking a cultures obsession with fame and popularity and struggling to think of anything worse than being recognised/constantly under surveillance.

As you said, context is everything. It is literally impossible to detect sarcasm reliably with only the sentence in which sarcasm is contained.

Re: Like an AI Could Ever Spot Sarcasm

#24

Post by aalleavitch » Wed, Jan 31, 2018, 11:31 PM UTC

Stratoscope wrote: post #8

Like a human being could ever read that text. If you're having as much trouble reading it as I was, open the developer tools and on the body style, remove "DINPro" from the font-family, turn off the font-weight: 300 or change it to 400, and increase the font-size to 16px or whatever size you like. If the AIs ever do take over, my one request is that they use plenty of sarcasm when they talk about designers who think…

This guy front-end develops

Re: Like an AI Could Ever Spot Sarcasm

#25

Post by ficklepickle » Wed, Jan 31, 2018, 11:41 PM UTC

RobertDeNiro wrote: post #13

civilian wrote: post #4

Sarcasm is a great tool. But there are a couple of people I know who never turn off their "Sarcastic tone", and it becomes impossible to tell what's genuine and what's bullshit. I try to tell them that their noise-to-signal ratio is bad, but they um... react defensively.

“sarcasm and jokes were often the bottle in which clinical depressives sent out their most plangent screams for someone to care and help them.”

So true. This was me, once upon a time. Unfortunately, it tends to have the opposite effect and push people away.

Re: Like an AI Could Ever Spot Sarcasm

#26

Post by skeleton » Wed, Jan 31, 2018, 11:42 PM UTC

Stratoscope wrote: post #21

com2kid wrote: post #18

Earlier quoted context omitted.

It actually looks quite nice in Firefox, it is hard to read in Chrome though. Maybe they have the one last web design team that primarily tests in FF? :D

I'm curious which OS you're using. On Windows, it looks pretty much equally bad to my eyes in Chrome, Firefox, and Edge.

It looks good for me in Firefox on Xubuntu 16.04.

Re: Like an AI Could Ever Spot Sarcasm

#27

Post by posterboy » Wed, Jan 31, 2018, 11:44 PM UTC

ateesdalejr wrote: post #3

Yes! I need alexa to be sarcastic.

That's irony, not sarcasm.

Re: Like an AI Could Ever Spot Sarcasm

#28

Post by cabalamat » Wed, Jan 31, 2018, 11:47 PM UTC

Sarcasm is almost certainly AI-complete. Consider this post: https://cabalamat.wordpress.com/2018/01/31/royal-mail-announ... which is pretty easy for a human to tell is sarcastic, but would be difficult for an AI unless it actually understood it.

Re: Like an AI Could Ever Spot Sarcasm

#29

Post by denzil_correa » Wed, Jan 31, 2018, 11:49 PM UTC

civilian wrote: post #4

Sarcasm is a great tool. But there are a couple of people I know who never turn off their "Sarcastic tone", and it becomes impossible to tell what's genuine and what's bullshit. I try to tell them that their noise-to-signal ratio is bad, but they um... react defensively.

> I try to tell them that their noise-to-signal ratio is bad, but they um... react defensively.

Defense mechanism could be one possible explanation.

Re: Like an AI Could Ever Spot Sarcasm

#30

Post by hinkley » Wed, Jan 31, 2018, 11:50 PM UTC

jboggan wrote: post #9

Last year we were working on a rubber ducky debugging chatbot and relying a bit too heavily on StackOverflow data for conversational training data. It frequently gave sarcastic answers, especially if you asked for help concerning regular expressions.

Name the bot Tony the Pony and call it a feature.