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 ๐
If your post meets the following criteria, it's welcome here!
- Open-ended question
- 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.
- Not regarding using or support for Lemmy: context, see the list of support communities and tools for finding communities below
- Not ad nauseam inducing: please make sure it is a question that would be new to most members
- An actual topic of discussion
Looking for support?
Looking for a community?
- Lemmyverse: community search
- sub.rehab: maps old subreddits to fediverse options, marks official as such
- !lemmy411@lemmy.ca: a community for finding communities
~Icon~ ~by~ ~@Double_A@discuss.tchncs.de~
founded 5 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
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:
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
Nah, it has the cadence and writing style of a highschool essay. No one really writes like that
I pity the few people who do. The advent of AI probably has everyone ignoring them and assuming they are a bot.
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???