this post was submitted on 11 Aug 2023
280 points (91.2% liked)

Asklemmy

43945 readers
593 users here now

A loosely moderated place to ask open-ended questions

Search asklemmy ๐Ÿ”

If your post meets the following criteria, it's welcome here!

  1. Open-ended question
  2. Not offensive: at this point, we do not have the bandwidth to moderate overtly political discussions. Assume best intent and be excellent to each other.
  3. Not regarding using or support for Lemmy: context, see the list of support communities and tools for finding communities below
  4. Not ad nauseam inducing: please make sure it is a question that would be new to most members
  5. An actual topic of discussion

Looking for support?

Looking for a community?

~Icon~ ~by~ ~@Double_A@discuss.tchncs.de~

founded 5 years ago
MODERATORS
 

How authentic are forums like these actually? With the rise of AI chatbots, internet interaction feels more fake than ever before. Why should I post here my opinions and thoughts, share articles etc. when probably most of you are just chatbots?

you are viewing a single comment's thread
view the rest of the comments
[โ€“] gerryflap@feddit.nl 6 points 1 year ago* (last edited 1 year ago) (3 children)

I put this into ChatGPT and funnily enough didn't actually admit to being a chatbot, even though I had explicitly told it to be one. (EDIT: Upon second try it did casually mention being a chatbot). It decided to comment this:

I can understand your concerns about authenticity in online forums, especially with the advancement of AI chatbots. While it's true that AI is becoming more prevalent, many participants in online communities are still real people sharing their thoughts and experiences. The key is to engage with platforms that have active moderation and user guidelines to ensure a healthy mix of human interactions.

As for your decision to post, it ultimately depends on your goals. Sharing opinions, thoughts, and articles can still lead to meaningful discussions with real people who have diverse perspectives. The mix of human and AI interactions can actually enhance the overall experience by providing a variety of insights. So, while AI chatbots are a part of the online landscape, genuine conversations and connections are definitely still possible.

Honestly though, it is quite concerning. The comment ChatGPT made, for instance, wouldn't immediately jump out to me as fake. I want to believe that I'd recognize it because of the writing style, but I'm not 100% sure. Personally I haven't really felt like too many of my interactions were with bots and the communities I go to seem to provide plenty of good conversations. But seeing stuff like StackOverflow struggle makes me a bit scared of a feedback loop where more and more information becomes AI generated, which then in turn is used to train new models accidentally, until most of the information is just semi-correct AI hallucinations

[โ€“] AOCapitulator@hexbear.net 5 points 1 year ago (1 children)

Nah, it has the cadence and writing style of a highschool essay. No one really writes like that

[โ€“] livus@kbin.social 1 points 1 year ago

I pity the few people who do. The advent of AI probably has everyone ignoring them and assuming they are a bot.

[โ€“] jandar_fett@lemmy.world 4 points 1 year ago

I went further still and fed your post into ChatGPT with this prompt: "Analyze this and tell me your prediction on the future of the internet keeping in mind the total enshittification of social media and most of the big tech companies apps and people as products mentality: "

& this is what I got back:

"The text you provided highlights the evolving landscape of AI chatbots and their potential impact on online interactions. As AI becomes more prevalent, distinguishing between human-generated and AI-generated content could become increasingly challenging. The concern about a feedback loop of AI-generated information perpetuating inaccuracies is valid. To mitigate this, it's crucial for platforms to maintain active moderation, user guidelines, and mechanisms for authentic human engagement. The future of the internet might involve a delicate balance between AI and human interactions, with responsible management of AI-generated content to ensure the preservation of genuine conversations and connections."

Does this increase or decrease your concern???