Can someone please bring back human telephone operators? I take it all back. I don't mind being shunted back and forth by real people. The soul-sucking pre-recorded voices, the endless waiting and back-and-forth through the labyrinth of unwanted options, the impotent rage and, ultimately, the zero time saved - none of it is worth it. The technology should be banned and criminalised. Bring back the human switchboardists! I don't care how dreadful or sociopathic they are - I miss them!
This is proof ChatGPT is fake as a $4 Bill. There is no pandemics nor nuclear wars, nor Aliens from Space nor Bigfoot. It's all "Fake News". You know, the definition of "AI". Artificial Intelligence... That means "Fake" or "counterfeit, imitative. not genuine; imitating something superior ; arranged, staged. deliberately arranged for effect". And so forth and so on.
More fear porn. How can AI possibly be more-than-human in some way if it's programmed by humans to reason and language like humans and trained on human data and human interpretations of that data? It's just an aggregator and imitator. So all it can possibly amount to is the sum total of human stupidity.
What makes humans more-than-human is their ability to channel a vastly greater intelligence and consciousness than our own which comes with being living systems continuous with and within living systems. The greatest of human art and inspiration and the greatest of human discoveries all originate in that realm. AI can't do that. It isn't alive.
The linked article is by Harvey Risch, not Martin Kulldorff, and is well-worth reading. To me the weirdest/scariest thing I've seen so far about AI is how it seems to be programmed to deliberately lie--as it did with Risch's inquiries. Just keeps making stuff up, and then "apologizes" when caught.
I have read several of these exchanges with ChatGPT and they all sound like a kind of whining excuse. "ooh, I'm just a po li'l robot algo and am still trying to get this stuff right, but I'm weak and tired and get mixed up, so sorry, sorry sorry...."
In a world devoid of meaning the zombies worship “the science” as defined by the masters. They begged for protection and begged the masters to take their souls in payment. The masters replied “we already have them” and begun the slaughter.
I've found ChatGPT is mostly a fancy chat bot. The reference database is pretty large but I've found it lacks reasoning skills. It's mostly information retrieval. I did use it to simplify some trig recently and write me some excel expressions but it regurgitates "settled science" on any interesting questions and refuses to speculate. I'm unsure if it's simply not capable or if it's been handcuffed, but I've been unimpressed so far.
I wonder if you accidentally triggered some ChatGPT Covid constraint/guardrail with this query by asking about "death rate".
Take a look at this (just tried it)
Prompt: If the success rate is 0.0003%, what is the chance of success?
ChatGPT:
To calculate the chance of success from a success rate of 0.0003%, we need to convert the percentage to a decimal.
0.0003% is equal to 0.000003 in decimal form (dividing by 10000).
Therefore, the chance of success is 0.000003, or 0.0003%. This means that for every 1,000,000 attempts, there would be an expected success in about 3 of them.
I wonder if s possible that in the consideration of the contextless death rate ChatGPT is working from the assumption that the real death rate is 100%, that is, every human being dies? In its spurious “guess” it takes 99,99997 as the closest estimate it could work out given the data you gave it? Or maybe it’s not that smart. But this will be the real problem will be given a truly complex calculation - no one will know when or why it’s wrong!
I think the author got the Chat bot that only went to Junior College for three months and then dropped out when it couldn't pass the general math requirement.
So, how does one get ChatGPT to end this loop of, "Once again, I apologize for the error in my previous explanation."?
Can someone please bring back human telephone operators? I take it all back. I don't mind being shunted back and forth by real people. The soul-sucking pre-recorded voices, the endless waiting and back-and-forth through the labyrinth of unwanted options, the impotent rage and, ultimately, the zero time saved - none of it is worth it. The technology should be banned and criminalised. Bring back the human switchboardists! I don't care how dreadful or sociopathic they are - I miss them!
This is proof ChatGPT is fake as a $4 Bill. There is no pandemics nor nuclear wars, nor Aliens from Space nor Bigfoot. It's all "Fake News". You know, the definition of "AI". Artificial Intelligence... That means "Fake" or "counterfeit, imitative. not genuine; imitating something superior ; arranged, staged. deliberately arranged for effect". And so forth and so on.
More fear porn. How can AI possibly be more-than-human in some way if it's programmed by humans to reason and language like humans and trained on human data and human interpretations of that data? It's just an aggregator and imitator. So all it can possibly amount to is the sum total of human stupidity.
What makes humans more-than-human is their ability to channel a vastly greater intelligence and consciousness than our own which comes with being living systems continuous with and within living systems. The greatest of human art and inspiration and the greatest of human discoveries all originate in that realm. AI can't do that. It isn't alive.
Martin Kuldorff had a similar experience ... https://brownstone.org/articles/my-conversation-with-ai-over-hydroxychloroquine/
The linked article is by Harvey Risch, not Martin Kulldorff, and is well-worth reading. To me the weirdest/scariest thing I've seen so far about AI is how it seems to be programmed to deliberately lie--as it did with Risch's inquiries. Just keeps making stuff up, and then "apologizes" when caught.
Ooops! My bad. You're right. Thanks for the correction.
I would have next asked AI if there was a way to get it to stop apologizing.
This is quite similar to a chat I had with a Ticketmaster chatbot earlier this week. No matter how you ask the question, you're not getting an answer.
I have read several of these exchanges with ChatGPT and they all sound like a kind of whining excuse. "ooh, I'm just a po li'l robot algo and am still trying to get this stuff right, but I'm weak and tired and get mixed up, so sorry, sorry sorry...."
Good point, made me smile.
In a world devoid of meaning the zombies worship “the science” as defined by the masters. They begged for protection and begged the masters to take their souls in payment. The masters replied “we already have them” and begun the slaughter.
More here; https://wakeuppeople.substack.com/p/the-psychological-war-in-your-mind
You sure you weren't talking to gates or fauci, or hotez, or walensky or joey? Live by the computer, die by the computer.
So it subtracted the probability from 1, rather than adding it to zero....
Wow.
I've found ChatGPT is mostly a fancy chat bot. The reference database is pretty large but I've found it lacks reasoning skills. It's mostly information retrieval. I did use it to simplify some trig recently and write me some excel expressions but it regurgitates "settled science" on any interesting questions and refuses to speculate. I'm unsure if it's simply not capable or if it's been handcuffed, but I've been unimpressed so far.
I wonder if you accidentally triggered some ChatGPT Covid constraint/guardrail with this query by asking about "death rate".
Take a look at this (just tried it)
Prompt: If the success rate is 0.0003%, what is the chance of success?
ChatGPT:
To calculate the chance of success from a success rate of 0.0003%, we need to convert the percentage to a decimal.
0.0003% is equal to 0.000003 in decimal form (dividing by 10000).
Therefore, the chance of success is 0.000003, or 0.0003%. This means that for every 1,000,000 attempts, there would be an expected success in about 3 of them.
I read a persuasive article that AI will be tightly regulated by our liars in charge to be another cudgel to prevent free speech.
No, thank you.
*it
I wonder if s possible that in the consideration of the contextless death rate ChatGPT is working from the assumption that the real death rate is 100%, that is, every human being dies? In its spurious “guess” it takes 99,99997 as the closest estimate it could work out given the data you gave it? Or maybe it’s not that smart. But this will be the real problem will be given a truly complex calculation - no one will know when or why it’s wrong!
I think the author got the Chat bot that only went to Junior College for three months and then dropped out when it couldn't pass the general math requirement.