[brindidrip]

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.

[darkwater]

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

[throwup]

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.

[rchaud]

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

[raxxorraxor]

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_2020]

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.

[SheinhardtWigCo]

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

[Arch-TK]

3, 5 and 7 seem awfully pessimistic no?

[zone411]

I'll take the under.

[warbler73]

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

0 years.

[spaceman_2020]

1 year for this tech to be incorporated into most cheap/free creative tools.

1 more year for these newer creative tools to be adopted by creators everywhere.

1 more year for the humans to completely give up.

You have to remember that tech takes time to permeate to the bottom rung. Most of my non tech friends haven’t even heard of Dall-E, let alone chatGPT.

[fragmede]

1 year? The Internet's already rife with SEO spam without ML algos creating convincing looking copy. They'll copy a site wholesale just with a different domain name. Spammers are probably already using this to generate copy for websites.

eg https://news.ycombinator.com/item?id=33640819

[arkitaip]

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]

[layer8]

> 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.

[rightbyte]

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

[dalmo3]

> the internet internet

I think you pass the Turing test. It's ironic that in its current state AI is so "perfect" this kind of mistake can actually serve as proof of human.

Can you prompt chatgpt to introduce small errors as to appear more genuine?

[rightbyte]

You can ask it to write like a teenager etc. It should be fairly trivial to make a script that removes ' and some . and maybe adds some writing mistake.

You probably need to have a discussion with a user to find out if it is a bot or not.

Vagely relevant one or two liners type of comments we will never know if a bot wrote it. The kind of noise people post on Twitter, Facebook and Reddit.

[9wzYQbTYsAIc]

> 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.

[cercatrova]

That's honestly a hilarious response from ChatGPT