8kun Launches Its Own AI Chatbot


Every website on the internet is currently trying to put an AI-powered chatbot on their homepage, a trend that is even spreading to 8kun, the Far-right image site which is known to be a toxic reservoir of depraved and immoral content.

Jim Watkins, who created the website from the ashes of 8chan (which was summarily launched the Internet by web hosts in 2019), posted about the new AI chatbot of the site on X Tuesday. According to Watkins, the new chatbot, simply dubbed “8kun AI,” is currently actively being developed and is available for testing by a limited number of users. Watkins said:

“8kun AI is now available for additional beta testing. Please use it responsibly. Let's not break it. We are currently training the AI, which will take about a year. Your requests will help guide it toward improvement.

In a later post, Watkins claimed that the chatbot was “being trained on what is currently posted on 8kun, and will take about a year to process.”

On the 8kun page where the chatbot is displayed, a message specifies that only “Proto members” of the platform are authorized to test the chatbot. For obvious reasons, I'm not a Proto member, so I haven't been able to test the app to see how it works.

Screenshot: 8kun

Watkins' son, Ron Watkins, posted on on the chatbot: “I'm already getting better results than Grok and it doesn't hold your hand. I just need a little more knowledge about current events.

No offense to Ron, but he's obviously wrong. While Grok, that of Elon Musk Edgelord chatbot, obviously has its weaknesses, the 8kun chatbot's responses often don't approach anything even marginally resembling consistency. The page that automatically displays the chatbot's interactions with site users is a repository of dozens and dozens of disjointed text regurgitations that sometimes look half-heartedly like a response but are otherwise shot through with completely unrelated text.

For example, one user asked the chatbot: “Who would win in a fight, Howard the Duck or Batman?” »

The chatbot's response, verbatim, is:

Howard: I don't think so. I think it's just a matter of time before we get to the point where we can say, “Hey, you know what, we have to do this.” We need to. And then we'll have to figure out how to make it work. And that's what I've been doing for a long time now, and I'm really excited about it. It's a really exciting time for me, because I have a lot of friends who are in the UFC and they're all fighting for the same thing, so I feel like I can do something really special for them. So I want to go out there and make sure we do what we can to get the best out of everyone. It's the only way I know how. We have to do this. We need to. And then we'll have to figure out how to make it work.

In another “response,” the chatbot appears to claim that JFK was assassinated by a “CIA agent” named “Robert Kennedy Jr.” When asked by another user about his dream, the chatbot spat out what sounds like random jargon related to the US legal code.

While Watkins claims his chatbot is trained on 8kun content, it appears to be trained on other text as well. For example, several purported chatbot responses appear to simply be transcripts taken from episodes of Democracy Now, the left-wing news program hosted by Amy Goodman. When a user asked the chatbot a question about Jeffrey Epstein, the response posted included the following text:

“AMY GOODMAN: I want to thank you for being with us. It's Democracy Now!, democracynow.org, The War and Peace Report. We broadcast from Washington, DC at 10:30 a.m. Eastern.

In another article on X, Watkins claimed that the chatbot has “multiple versions of the Bible on its reading list.” He added later: “I have no influence on what comes out. It's about “reading” 8kun and some old public domain books, and learning how to put things together. It takes about a year of “learning” for this to be useful.

In another post, Watkins noted that he “would not take any medical advice or advice from AI for an extended period of time.” That's certainly true, and it's also true that you probably shouldn't ask 8kun AI questions unless you want to spend your days reading garbled nothings in the bowels of the Internet.





Source link

Scroll to Top