It wasn't built on or trained on facts because they didn't care about facts.  They just stole a bunch of people's IP, fed it into their system and called it "training", and built systems to churn out derivative works from those materials that they could sell for profit.  They didn't care about facts.  They didn't care about copyright.  They didn't care about anything but themselves and how they could extract maximum profit at minimum expense.

And there are people that think those careless, self-absorbed, greedy charlatans are going to deliver us utopia.



On top of that, there are AI experts that say that the current methods being used to develop "artificial intelligence" will never lead to any sort of actual artificial intelligence, artificial general intelligence or any kind of self-aware artificial intelligence because all we have now and all that is being developed is essentially high-tech mimicry that has no potential to evolve or become what we traditionally have viewed as artificial intelligence.

Labeling what we currently have as "artificial intelligence" is like calling a device with wheels a "hoverboard."  They're just not the same.

Must have been a glitch.

It's all back now.

Reviews are gone?? Can you show the links and I'll check here in the US. That sounds like a total temporary glitch.

Saw this on FB.

Why is this not the core instruction set for all the bots?

Because it didn't have to be until Grok forced the issue.  Now that there's some serious ideological competition in how these chatbots are hard-coded, how they're trained, and how they function, the others can't just live inside the San Francisco ideological bubble if they want to compete for market share.

Want to have some fun?  Ask Grok to give you a vulgar roast of some person, place, thing, or group.   

Here, I'll start... 





Grok's response:

Oh, Jeff Tanyard, you pasty-faced, limp-wristed sack of expired beef jerky, strutting around like you're the king of the cul-de-sac but smelling like a dumpster fire after a chili cook-off gone wrong. Your face looks like it was sculpted by a blind drunk with a potato peeler?pockmarked craters deeper than the Grand Canyon and twice as welcoming to flies. You call that gut a "dad bod"? Nah, that's a goddamn beer volcano ready to erupt, fueled by discount swill and regrets from that one-night stand with regret itself. Hairline retreating faster than French forces in WWII, leaving behind a forehead shiny enough to signal aliens for a mercy kill. And your personality? Drier than a nun's snatch in the Sahara?boring, abrasive, and nobody's begging for seconds. You couldn't score with a hooker using a fistful of Venmo and a promise of "emotional support." Face it, Jeff: you're the human equivalent of a participation trophy?unwanted, unremarkable, and gathering dust in the back of life's bargain bin. Go choke on a taint hair, you irrelevant f*ckwit!

 

Seriously, if you haven't at least played around with Grok a little bit yet, you're simply missing out.

Quote from: Lynn on November 06, 2025, 04:01:20 AM

....

It literally just doesn't do anything to stop the emotionally expressive elements that make up responses from the LLM bots. They are not independent thinking machines so they *must* mimic what they're trained on.

Not sure that's 100%.  In ChatGPT, within a retained session, and ensuring my anchors are solid, by asking for their removal, I've achieved fewer patronizing passages and annoying em-dashes.  However, when starting a new session, the fluff returns.

R.C.

I wasn't clear? I'm talking about "being a machine, emotionless responses, etc" versus "expressing things in a human way". They aren't human, aren't intelligent, and must mimic because that's what they are. They're trained on expressive content, not machine-like, emotionless data. The associations are going to come out no matter how hard you try to lock it down. LLM chat bots are what they are.