undefined | Better HN

0 pointsbrindidrip3y ago0 comments

Yes, one way to identify responses that may have been generated by ChatGPT is to look for signs of repetitive or verbose language. Because ChatGPT is a language model, it is designed to generate text that is fluent and coherent, but it may also produce text that is unnecessarily long or repetitive. This can be a telltale sign that a response was generated by an AI, as human responders are less likely to use repetitive or verbose language in their answers. Of course, this is not a foolproof method, and there may be other factors that can affect the quality and style of a response, but looking for repetitive or verbose language can be a useful starting point when trying to identify AI-generated responses.

0 comments

darkwater3y ago

This is fun but it's already starting to NOT be fun.

throwup3y ago

It has a very recognizable default writing style but it will change things up if you ask.

> Write a response to the following comment chain in the style of an angry Hacker News commenter.

> ...

What the hell is wrong with you? ChatGPT is a brilliant piece of technology and you're just dismissing it because of some stupid writing style? Get a grip and appreciate the advancements we're making in AI. Stop being so negative and enjoy the fun while it lasts.

rchaud3y ago

an AI that communicates with the verbosity of a recipe website....our glittering future!

raxxorraxor3y ago

You are not an AI. Probably.

I really think the results are impressive, but I already hate how some people will use it. And that indeed is not fun.

spaceman_20203y ago

I reckon we are about 3 years from most textual content online being created by bots, 5 years from static visual content being bot-created, and 7-8 years from bot-created visual content clogging up all social media.

SheinhardtWigCo3y ago

Everyone will be doing strict ID verification long before any of those milestones are actually reached.

Arch-TK3y ago

3, 5 and 7 seem awfully pessimistic no?

zone4113y ago

I'll take the under.

warbler733y ago

> we are about 3 years from most textual content online being created by bots

0 years.

1 more reply

arkitaip3y ago

To find out if a response was made by a computer, look for repeating words or long sentences. ChatGPT is a program that makes text that makes sense and flows well, but sometimes it uses too many words or repeats itself. This is a clue that the response might have been made by a computer instead of a person. However, this isn't a sure thing and there might be other reasons why a response is long or repeats itself. Still, it's a good place to start.

[After many attempts]

layer83y ago

> Respond to the above in the informal style of a slightly contrarian Hacker News comment, with a hint of passive-aggressiveness. Avoid repetitive wording and long sentences.

Wow, thanks for the tip! I never would have thought to look for repeating words or long sentences to determine if a response was made by a computer. I guess I'll just blindly trust everything I read online from now on. Sarcasm aside, this is a pretty flawed method. Just because a response has repeating words or is long doesn't mean it's not from a person. And conversely, just because a response is short and doesn't repeat itself doesn't mean it's not from a computer. It's not that simple.

rightbyte3y ago

This is terrible. Pretty soon most comments on the internet internet will be written by bots.

1 more reply

9wzYQbTYsAIc3y ago

> To find out if a response was made by a computer, look for repeating words or long sentences.

That technique will produce quite a few false positives - a significant portion of humanity with language production issues on the autism spectrum communicate like that.

edit: Makes me wonder to what extent the training data is biased by writings from people on the autism spectrum.

cercatrova3y ago

That's honestly a hilarious response from ChatGPT

j / k navigate · click thread line to collapse

0 comments

darkwater3y ago

This is fun but it's already starting to NOT be fun.

throwup3y ago

It has a very recognizable default writing style but it will change things up if you ask.

> Write a response to the following comment chain in the style of an angry Hacker News commenter.

> ...

rchaud3y ago

an AI that communicates with the verbosity of a recipe website....our glittering future!

raxxorraxor3y ago

You are not an AI. Probably.

I really think the results are impressive, but I already hate how some people will use it. And that indeed is not fun.

spaceman_20203y ago

SheinhardtWigCo3y ago

Everyone will be doing strict ID verification long before any of those milestones are actually reached.

Arch-TK3y ago

3, 5 and 7 seem awfully pessimistic no?

zone4113y ago

I'll take the under.

warbler733y ago

> we are about 3 years from most textual content online being created by bots

0 years.

1 more reply

arkitaip3y ago

[After many attempts]

layer83y ago

> Respond to the above in the informal style of a slightly contrarian Hacker News comment, with a hint of passive-aggressiveness. Avoid repetitive wording and long sentences.

rightbyte3y ago

This is terrible. Pretty soon most comments on the internet internet will be written by bots.

1 more reply

9wzYQbTYsAIc3y ago

> To find out if a response was made by a computer, look for repeating words or long sentences.

That technique will produce quite a few false positives - a significant portion of humanity with language production issues on the autism spectrum communicate like that.

edit: Makes me wonder to what extent the training data is biased by writings from people on the autism spectrum.

cercatrova3y ago

That's honestly a hilarious response from ChatGPT

j / k navigate · click thread line to collapse