Looking forward to Deep Sarcasm...
Like an AI Could Ever Spot Sarcasm
81–90 of 109 posts
Re: Like an AI Could Ever Spot Sarcasm
#82Like 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
Please don't take personal swipes or post unsubstantive comments.
Re: Like an AI Could Ever Spot Sarcasm
#83Can't wait for the first next gen AI programming language to support an "as if" statement.
Re: Like an AI Could Ever Spot Sarcasm
#84This is neat. Sarcasm is hard because it's a violation of the cooperative principle. I think describing it as simply incongruity is understating the difficulty of the problem (that said, good enough for 80% accuracy on the task is nothing to sniff at). In communication, you've got two systems attempting to convey their internal, unobservable states to eachother. This happens across a number of different channels, eac…
That's a very good summary. I would say based on my experience on the internet, that spotting sarcasm is frequently beyond human capability, so it's not realistic to do it with an AI any time soon. Besides communicating with a recipient, subverting the cooperative principle can also be used to selectively communicate with one recipient out of many, or to mislead some or all. A lot of things people want to calculate t…
> I would say based on my experience on the internet, that spotting sarcasm is frequently beyond human capability ...
In a 1983 Usenet FAQ by Jerry Schwarz: "Avoid sarcasm and facetious remarks."
More recently, aka Poe's Law.
Re: Like an AI Could Ever Spot Sarcasm
#85Last 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.
"Use jQuery"
Re: Like an AI Could Ever Spot Sarcasm
#86Last 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.
Did it respond with Zalgo if you asked about Regex and HTML? https://stackoverflow.com/questions/1732348/regex-match-open...
He comes.
Re: Like an AI Could Ever Spot Sarcasm
#87Last 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.
That sounds like a pretty good result. Yandex has released it's voice assistant a few months ago (wasn't big news here on HN because it's Russian-only), and one feature that separated it from all the rest was sarcasm and kind of dark humor it acquired. Wouldn't you want your chatbot to be sarcastic sometimes?
Re: Like an AI Could Ever Spot Sarcasm
#88It'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).
In a standup context I'd read the continuation as sarcasm as well, as a part of a stream of jokes to come.
Re: Like an AI Could Ever Spot Sarcasm
#89If humans can’t identify sarcasm, why would you expect AI to? It’s like expecting AI to read handwriting, when people can’t even do that 100% of the time.
If humans can’t do simple math, why would you expect computers to?
It’s like expecting AI to sum up 1000 integers without errors, when people can’t even do that 100% of the time.
Re: Like an AI Could Ever Spot Sarcasm
#90If humans can’t identify sarcasm, why would you expect AI to? It’s like expecting AI to read handwriting, when people can’t even do that 100% of the time.
If humans can’t do simple math, why would you expect computers to? It’s like expecting AI to sum up 1000 integers without errors, when people can’t even do that 100% of the time.
There are some things easier for a computer to do, like lots of simple math, given that the computer can accurately store the result of each calculation, whereas people have difficulty doing so for 1000 integers.
And there are some things that are relatively easy for humans to do, like communicate with natural language. Sarcasm falls into the later category. This is because human understanding is heavily social and conceptual.