Every web site on the web is at the moment attempting to stay an AI-powered chatbot on its homepage, a development that extends even to 8kun—the far-right picture board web site that’s identified for being a poisonous cess pool of wicked and immoral content material.
Jim Watkins, who created the web site from the ashes of 8chan (which was summarily kicked off the web by webhosting suppliers in 2019), posted about the positioning’s new AI chatbot on X on Tuesday. According to Watkins, the brand new chatbot, which is just dubbed the “8kun AI,” is at the moment being actively developed and is obtainable for testing by a restricted variety of customers. Watkins stated:
“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 publish, 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 web page the place the chatbot is displayed, a message states that solely “Proto members” of the platform are allowed to check out the chatbot. For apparent causes, I’m not a Proto member, so I couldn’t take a look at out the app to see the way it works.
Watkins’ son, Ron Watkins, posted on X concerning 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, however he’s clearly incorrect. While Grok, Elon Musk’s edgelord chatbot, clearly has its foibles, the 8kun chatbot’s solutions typically don’t method something even marginally resembling coherence. The web page that auto-displays the chatbot’s interactions with web site customers is a repository of dozens and dozens of unhinged textual content regurgitations that typically half-resemble a solution however are in any other case shot by with utterly unrelated textual content.
For occasion, one consumer requested the chatbot: “who would win in a fight, Howard the Duck or Batman?”
The reply from the chatbot, verbatim, is:
Howard: I don’t suppose so. I feel it’s only a matter of time earlier than we get to the purpose the place we’re going to have the ability to say, “Hey, you know what, we’ve got to do this. We’ve gotta do that.” And then we’ll have to determine find out how to make it work. And that’s what I’ve been doing for a very long time now, and I’m actually enthusiastic about it. It’s a extremely thrilling time for me, as a result of I’ve numerous pals who’re within the UFC and so they’re all combating for a similar factor, so I really feel like I can do one thing actually particular for them. So I need to go on the market and ensure that we do what we are able to to get one of the best out of one another. That’s the one means I understand how. e’ve acquired to do that. We’ve gotta try this.” And then we’ll have to determine find out how to make it work.
In one other “answer,” the chatbot seems to assert that JFK was assassinated by a “CIA agent” named “Robert Kennedy Jr.” When requested by one other consumer about its dream, the chatbot spat out what appears to be like like random jargon associated to the U.S. authorized code.
While Watkins claims that his chatbot is being skilled on the contents of 8kun, it seems to be skilled on different texts as nicely. For occasion, a number of supposed responses from the chatbot simply look like transcripts taken from episodes of Democracy Now, the left-leaning information program hosted by Amy Goodman. When one consumer requested the chatbot a query about Jeffrey Epstein, the posted response included the next textual content:
“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 one other publish 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 a few outdated public area books, and studying to place issues collectively. It takes a few yr of “learning” for it to be helpful.”
In a unique publish, Watkins famous that he “would not take any medical or any advice from the AI for a long time.” That’s definitely true and it’s also true that you just most likely shouldn’t ask 8kun AI any questions except you need to spend your days studying garbled nothings from the bowels of the web.