8kun Launches Its Own AI Chatbot

Key Takeaways:

– The trend of incorporating AI-powered chatbots on websites extends even to controversial platforms like 8kun.
– Jim Watkins, the creator of 8kun, announced the development of the “8kun AI” chatbot for beta testing.
– The chatbot is being trained on the content posted on 8kun and is expected to take about a year to fully process.
– Only “Proto members” of 8kun are allowed to test the chatbot.
– Ron Watkins, Jim’s son, claimed that the 8kun chatbot is already outperforming Grok, Elon Musk’s chatbot.
– However, the chatbot’s responses often lack coherence and contain unrelated text.
– It appears that the chatbot might be trained on texts beyond 8kun, including transcripts from Democracy Now.
– Watkins stated that the chatbot has several versions of the Bible on its reading list.
– Watkins advised against seeking medical or any other type of advice from the AI for the time being.

Gizmodo:

Every website on the internet is currently trying to stick an AI-powered chatbot on its homepage, a trend that extends even to 8kun—the far-right image board website that is known for being a toxic cess pool of depraved and immoral content.

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

“The 8kun AI is now available for further beta testing. Please use it responsibly. Let’s not break it. We are currently in the process of training the AI, which will take approximately a year. Your inquiries will help guide it toward improvement.”

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

On the 8kun page where the chatbot is displayed, a message states that only “Proto members” of the platform are allowed to test out the chatbot. For obvious reasons, I am not a Proto member, so I could not test out the app to see how it works.

Screenshot: 8kun

Watkins’ son, Ron Watkins, posted on X about the chatbot: “Already getting better results than Grok and it doesn’t hold your hand. Just needs a bit more knowledge about current events.”

No offense to Ron, but he is obviously wrong. While Grok, Elon Musk’s edgelord chatbot, obviously has its foibles, the 8kun chatbot’s answers often don’t approach anything even marginally resembling coherence. The page that auto-displays the chatbot’s interactions with site users is a repository of dozens and dozens of unhinged text regurgitations that sometimes half-resemble an answer but are otherwise shot through with completely unrelated text.

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

The answer from the chatbot, 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’re going to be able to say, “Hey, you know what, we’ve got to do this. We’ve gotta do that.” 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 that we do what we can to get the best out of each other. That’s the only way I know how. e’ve got to do this. We’ve gotta do that.” And then we’ll have to figure out how to make it work.

In another “answer,” the chatbot appears to claim that JFK was assassinated by a “CIA agent” named “Robert Kennedy Jr” (you know, the President’s brother). When asked by another user about its dream, the chatbot spat out what looks like random jargon related to the U.S. legal code.

While Watkins claims that his chatbot is being trained on the contents of 8kun, it appears to be trained on other texts as well. For instance, multiple supposed responses from the chatbot just appear to be transcripts taken from episodes of Democracy Now, the left-leaning news program hosted by Amy Goodman. When one user asked the chatbot a question about Jeffrey Epstein, the posted response included the following text:

“AMY GOODMAN: I want to thank you for being with us. This is Democracy Now!, democracynow.org, The War and Peace Report. We’re broadcasting from Washington, D.C. at 10:30 a.m. Eastern time.”

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

In a different post, Watkins noted that he “would not take any medical or any advice from the AI for a long time.” That’s certainly true and it is also true that you probably shouldn’t ask 8kun AI any questions unless you want to spend your days reading garbled, incoherent garbage.


Source link

AI Eclipse TLDR:

The far-right image board website 8kun has introduced an AI-powered chatbot called “8kun AI,” which is currently being developed and tested by a limited number of users. The chatbot, created by Jim Watkins, the creator of 8chan, is being trained on the content posted on 8kun as well as other texts. However, the chatbot’s responses often lack coherence and contain unrelated text. Users have reported receiving answers that do not make sense or include random jargon. Watkins stated that the training process will take about a year and that the chatbot is not reliable for medical or any other advice.