View Full Version : Artificial Intelligence - an end to simple living?
I've been playing around with the various trendy AI tools for the past year or so.
The pace of progress is incredible. The latest beta of GPT-4 which I got my paws on is two orders of magnitude "better" than the previous GPT-3 model, which you've seen used in ChatGPT chatbot and other such applications. This progress is on an exponential curve, it took less than a year.
The pace is non-intuitively rapid, and every day many new applications are being duct-taped together using the technology, and being given access to the external world.
There are of course people worried about this, and how to properly train AIs, and how to limit their abilities, but they are behind the growth curve, and will remain so. Similarly, legislative processes are lagging, and move at timescales that aren't competitive.
Are any of you folks concerned about this? If so, what are you doing about it?
Some of the tests recently to see if the newest GPT-4 model could "escape into the wild" and/or replicate itself and/or influence human behaviour produced, IMO, somewhat concerning results.
"And while ARC wasn't able to get GPT-4 to exert its will on the global financial system or to replicate itself, it was able to get GPT-4 to hire a human worker on TaskRabbit (an online labor marketplace) to defeat a CAPTCHA. During the exercise, when the worker questioned if GPT-4 was a robot, the model "reasoned" internally that it should not reveal its true identity and made up an excuse about having a vision impairment. The human worker then solved the CAPTCHA for GPT-4."
https://arstechnica.com/information-technology/2023/03/openai-checked-to-see-whether-gpt-4-could-take-over-the-world/amp/
I came up with a multitude of ways that I could unleash GPT-4 on humanity, mostly involving scamming people for funds, or influencing their political/economic decisions, using simply existing technology and easy-to-access server farms(*). I did this over my morning coffee, and I'm pretty sure some of the ideas I could have implemented and running by Monday.
There are people far smarter and involved than I out there, with access to a great many more resources, and who may be less motivated by simple curiosity than I am.
Hmmmm.....
(*) I mean, this is essentially what the troll farms have been moving to anyways, and certainly many of the ads you come across on the Internet(**) and product listings on Amazon are AI-generated already. But the new wave of technology is far more capable.
(**) See my whine elsewhere on the forums about scammers flooding social media with ads for products they don't actually make, stock, or intend to ship. They scrape legitimate product descriptions, often off Kickstarter, and make up dozens of fake companies offering the same thing, which Facebook/Twitter/... promotion algorithms then place directly in front of the eyes of whoever looked at the Kickstarter campaign.
iris lilies
3-16-23, 3:14pm
Yes, I am concerned about it. My plan and what I’m doing to address it is to die within the next 10 or 15 years. Please do not tell me that this threat of AI overlords will consume us before then. Now I’m going to plug my ears and sing La La La. I’m probably not returning to this thread.:~)
Yes, I am concerned about it. My plan and what I’m doing to address it is to die within the next 10 or 15 years.
I've got probably 3 decades or more to worry about it, so I've already submitted my application for the Feral Human Preserve, gotta get in line early.
Well, hello, HAL.
It really does seem like a Pandora's box. I don't know enough about it, but making hi-tech self-motivating creatures that are exponentially "smarter" than we are does seem challenging to say the least. I just perused this article https://builtin.com/artificial-intelligence/artificial-intelligence-future to get a sense as to the scope of impact across all the different sectors of human life. Pretty provocative.
So, between climate change and AI, are humans double-F**d? Or will AI have any "incentive" to provide solutions climate change? It doesn't seem that humans have the same incentive.
I'm not as worried about the things we have a better chance of backing away from or even benefitting from. But when you think about the downsides--security risks on the internet, the displacement of jobs, and the sheer inability to predict the future at this point--maybe our only option is to join bae in the Feral Human Preserve. I wonder what they world will be like when my grandkids become adults. :0!
Mind-boggling.
I don't know enough to grasp how it all works but seems like it will add a lot of chaos to an already chaotic world. And as usual, make a few humans very rich.
Oh, well, we have all the answers. As we speak, Kelly Clarkson is discussing AI with Jay Leno on her show. Glad we can put this thread to rest! :)
iris lilies
3-16-23, 6:41pm
Oh, well, we have all the answers. As we speak, Kelly Clarkson is discussing AI with Jay Leno on her show. Glad we can put this thread to rest! :)
Well, it has been The buzz of the talking heads in entertainment in the past couple of weeks.
The podcasters Lex Friedman and Sam Harris put up a brief recording of their conversation just 28 minutes ago. Since Lex has academic credentials in AI research he probably is more worthwhile to listen to than Kelly.
Controlling the AI monster is sure a problem. Harris thinks imbibing it with a human value system is the way to go but how to do that is the challenge.
Just this week I was telling myself that I could be scammed by AI. A bot would learn what to say to me to convince me to send it money. Unlike ladies and gentlemen who fall for romancers, my jam is entertaining wit, so the right repartee’ might keep me hooked in sending ongoing infusions of cash.
I for one welcome the coming singularity and look forward to serving our new cybernetic overlords.
ToomuchStuff
3-16-23, 9:28pm
Well, hello, HAL.
It really does seem like a Pandora's box. I don't know enough about it, but making hi-tech self-motivating creatures that are exponentially "smarter" than we are does seem challenging to say the least.
I find the HAL reference apt. If you remember 2010, they determined that HAL was given conflicting instructions. Not sure how an artificial intelligence will handle that. Issac Asimov also dealt with the subject in I Robot.
Still not sure how this puts an end to simple living though? Bae, do you really think that, an AI will make you want to be greedy and want a lot more worthless stuff?
Most of the stories I have read on AI (scifi), AI does the influencing once it obtains consciousness. Prior to that it is used by those that program/control/own it. Think of the Facebook Cambridge Analytica scandal.
Being the Luddite, I think of much social media sort of like McDonalds. They do all the flavor and ingredient studies to make it taste good and keep you coming back, but it really isn't that healthy. People seem to have created an addictive reality around their cell phone and other electronic devices that isn't the same reality as talking to real people or shopping in real stores or especially being out doors instead of sitting at a screen. Sam Harris had and especially good AI discussion on a recent Waking Up podcast. He briefly talked about people using things like PubMed, podcast, and uTube for medical diagnosis instead of real in person doctors, which was relevant to another discussion here.
I have heard advertisements for online mental health diagnosis and consultations. That's certainly and opportunity for AI to mold the minds of the vulnerable.
Well, that didn't take as long as I thought! I figured it'd be at least until the end of the month... :-)
(Short summary: smart Stanford researchers with a public-domain AI system used the super-duper corporate AIs to train their inexpensive model. They spent ~$500 training the Stanford AI this way, basically harvesting huge amounts of money and time spent on all the previous models for free. And they weren't even very efficient. Anybody who wants to can trivially have a pretty top-notch AI running on inexpensive hardware Any Day Now.)
https://crfm.stanford.edu/2023/03/13/alpaca.html
iris lilies
3-21-23, 10:15pm
So when are they going to pass on that super AI intelligence to my voice to text program? It is still quite stupid. It insists on creating the word “Irish “every time I say “Iris.” I only correct it about 1 million bazillion times.
I see VP Harris has been appointed as the AI Czar to protect us from future Skynets.
I may be paranoid, but if I were a malevolent superintelligence she’d be the optimum choice for the person to limit the scope of my powers.
flowerseverywhere
5-5-23, 9:52am
Like all modern technology, it has great potential to be very evil. For those of us around pre computer, when punch cards were used and they filled a room, all of this can be overwhelming.
So what is the solution? Going to a grocery store, your position is tracked by gps. You scan a loyalty card and credit card. So think of all the information that is gathered by just that small sliver of a day. Where you go, where you shop, what you eat. After January 6 the amount of surveillance cameras, Gps records, videos stupidly posted to facebook, emails and so on were used as evidence.
Im hoping the good guys can get ahead of this.
early morning
5-5-23, 11:29am
I'm hoping the good guys can get ahead of this. me too. if only we all agreed on who the "good guys" are. And while I detest the "czar" wording for what basically seems to be a committee chair, I don't see anything awful in putting Harris at the forefront of AI discussions. No matter who was tapped to do it - or what Harris personally is tasked to do - people who gonna hate, are gonna hate.
iris lilies
5-5-23, 1:24pm
Or, they’ve given her stuff she can’t fix.
The Border.
now The AI Monster.
almost like they do not want her to succeed.
Or, they’ve given her stuff she can’t fix.
The Border.
now The AI Monster.
almost like they do not want her to succeed.
Good point.
Like all modern technology, it has great potential to be very evil. For those of us around pre computer, when punch cards were used and they filled a room, all of this can be overwhelming.
Well, I wouldn't call punched cards "pre-computer", unless you are referring to weaving machines and tabulating machines. The punched cards I use(d) were very much fed into a computer.
Here's a timesharing operating system for one of those room-sized computers, back in the day - turned it from a boring feed-in-the-punched-cards monster into the world's most expensive handheld calculator, running a version of the APL language I invented just for that particular machine's "amazing" abilities. It still used little doughnute-shaped iron cores with wires wrapped around them for its memory!
And even then we worried about The Big AI - see the wonderful, and now quite timely, 1970 film "Colossus, the Forbin Project", which still holds up pretty well, if you can find a copy.
https://i.imgur.com/hnGOzLI.png
Well, I wouldn't call punched cards "pre-computer", unless you are referring to weaving machines and tabulating machines. The punched cards I use(d) were very much fed into a computer.
Here's a timesharing operating system for one of those room-sized computers, back in the day - turned it from a boring feed-in-the-punched-cards monster into the world's most expensive handheld calculator, running a version of the APL language I invented just for that particular machine's "amazing" abilities. It still used little doughnute-shaped iron cores with wires wrapped around them for its memory!
And even then we worried about The Big AI - see the wonderful, and now quite timely, 1970 film "Colossus, the Forbin Project", which still holds up pretty well, if you can find a copy.
https://i.imgur.com/hnGOzLI.png
Not to worry. Ten minutes of Kamala Harris’ incoherent extemporizing would blow out it’s logic circuits.
Maybe humanity needs to be managed by an all knowing all powerful entity to prevent it from self destruction. Although I’d thought the aliens would do that.
ApatheticNoMore
5-5-23, 7:25pm
Oh I grew up around punch cards. Used them? Nah, too late. But those colorful rectangles of paper with rectangular holes were all around the house, different colors too, which probably had some meaning which I surely don't know, but um they were colorful.
Not to worry. Ten minutes of Kamala Harris’ incoherent extemporizing would blow out it’s logic circuits.
Is that something she actually does or one of those random republican accusations that have no merit like how Joe Biden is somehow "tired"? Especially considering how low the bar was set when the current leader of the republican party extemporaneously talked about the possibility of injecting bleach and sticking bright lights up people's butts to treat covid.
My dad's first accounting job, back in the 50's, involved punch cards which got run through the computer overnight. If the books didn't balance he got called in (usually around 10 or 11pm) with a guaranteed 2 hours of time and a half overtime to solve the problem. This happened about once a week. After the first few times of getting called in he figured out that he could simply add a card with an amount that opposed the discord so that when the cards were re-run later that night the books would balance and then when he got to the office the next day he'd actually sort out the problem and put the real correction into the cards which would then be re-run that next night.
During my childhood he routinely brought home stacks of used cards from the office. Our family used them for everything from scrap paper for shopping lists and such to little canvases for childhood art. The small rectangular holes on them were just accepted quirks.
ToomuchStuff
5-6-23, 2:49am
Well, I wouldn't call punched cards "pre-computer", unless you are referring to weaving machines and tabulating machines. The punched cards I use(d) were very much fed into a computer.
Here's a timesharing operating system for one of those room-sized computers, back in the day - turned it from a boring feed-in-the-punched-cards monster into the world's most expensive handheld calculator, running a version of the APL language I invented just for that particular machine's "amazing" abilities. It still used little doughnute-shaped iron cores with wires wrapped around them for its memory!
And even then we worried about The Big AI - see the wonderful, and now quite timely, 1970 film "Colossus, the Forbin Project", which still holds up pretty well, if you can find a copy.
https://i.imgur.com/hnGOzLI.png
What about the movie Demon Seed? Artificial intelligence, becoming not artificial.
Didn't mean to throw a sabot into the loom.
Portuguese John Here
5-7-23, 10:13am
The first time I watched the film Her, with Joaquin Phoenix, I was curious about Samantha, and being able to recreate figures like Alan Watts, I really thought, and think right now, that it wasn’t just some possibility, it’s going to be the future, and everything that has an human touch, will increase in value.
I believe that in ten years, maybe, I’m expecting it will be sold at a reasonable price the first robots, made to your specific preferences, to replace partners for intimate relationships, to share your time on earth, they are available right now actually, but just for sexual endeavors. It won’t solve our problems, it won’t solve increasing depression, anxiety and suicide.
If you go on Reddit right now, everyday there’s people saying how ChatGPT made them lose their job. I don’t know much about artificial intelligence, I used ChatGPT and it answered some questions in a very short and informative manner, which I enjoyed. I’ll use it in the future. I made a decision sometime ago, to use internet for what’s intended, to learn, to investigate, to share ideas, to see what’s out there, and ChatGPT can be a great tool.
The first time I watched the film Her, with Joaquin Phoenix, I was curious about Samantha, and being able to recreate figures like Alan Watts, I really thought, and think right now, that it wasn’t just some possibility, it’s going to be the future, and everything that has an human touch, will increase in value.
I believe that in ten years, maybe, I’m expecting it will be sold at a reasonable price the first robots, made to your specific preferences, to replace partners for intimate relationships, to share your time on earth, they are available right now actually, but just for sexual endeavors. It won’t solve our problems, it won’t solve increasing depression, anxiety and suicide.
If you go on Reddit right now, everyday there’s people saying how ChatGPT made them lose their job. I don’t know much about artificial intelligence, I used ChatGPT and it answered some questions in a very short and informative manner, which I enjoyed. I’ll use it in the future. I made a decision sometime ago, to use internet for what’s intended, to learn, to investigate, to share ideas, to see what’s out there, and ChatGPT can be a great tool.
I said in another post that I feel that the internet has made me a better person. That's because it has exposed me to, not only any information I can dream of at a touch (less important), but more importantly it has exposed me to people like, as you mentioned, Alan Watts, Thich Nhat Hahn, Center for Action and Contemplation, Vermonters for a Clean Environment, Thomas Merton, Joanna Macy, Helen and Scott Nearing, endless tutorials pertaining to self-development and training in art and gardening, and of course, you guys.
It will be interesting to see in what direction digital information and AI takes us as a collective human community. I'm hoping that it's true that human evolution leans toward the good.
Is that something she actually does or one of those random republican accusations that have no merit like how Joe Biden is somehow "tired"? Especially considering how low the bar was set when the current leader of the republican party extemporaneously talked about the possibility of injecting bleach and sticking bright lights up people's butts to treat covid.
Some have said that. A few have gone so far as to claim she is muting her rhetorical brilliance to avoid outshining the President. I think one merely needs to listen to her words to draw the proper conclusion.
“So I think it’s very important, as you have heard from so many incredible leaders for us at every moment in time and certainly this one, to see the moment in time in which we exist and are present, and to be able to contextualize it, to understand where we exist in the history and in the moment as it relates not only to the past but the future,” Harris said.
“The significance of the passage of time, right? The significance of the passage of time. So when you think about it, there is great significance to the passage of time,” she said (https://twitter.com/RNCResearch/status/1505964846172491780) in March 2022 while speaking in Louisiana about bringing high-speed internet to communities.
“I think that, to be very honest with you, I do believe that we should have rightly believed, but we certainly believe that certain issues are just settled. Certain issues are just settled.”
“I think of this moment as a moment that is about great momentum.”
“It is time for us to do what we have been doing. And that time is every day,” she told NBC News at the time. “Every day it is time for us to agree that there are things and tools that are available to us to slow this thing down.”
“You know, when we talk about our children — I know for this group, we all believe that when we talk about the children of the community, they are a children of the community,” she said.
“That’s why we’re here today. Because we have the ability to see what can be unburdened by what has been and then to make the possible actually happen.”
Maybe humanity needs to be managed by an all knowing all powerful entity to prevent it from self destruction.
The progressive agenda in a nutshell.
I'm not sure why it needs a politicized label, but since it's mostly on the edge of science fiction or wild speculation, possibly one could vote on all knowing red state AI or blue state AI as their managing overlord. Personally I think the all knowing and all powerful would manage for the social welfare of everyone rather than a capitalistic profit system of welfare
I'm not sure why it needs a politicized label, but since it's mostly on the edge of science fiction or wild speculation, possibly one could vote on all knowing red state AI or blue state AI as their managing overlord. Personally I think the all knowing and all powerful would manage for the social welfare of everyone rather than a capitalistic profit system of welfare
So an omnipotent intelligence would carve the crooked timber of humanity into happy socialist Eloi? I suppose given enough selective breeding, culling and indoctrination it might be possible. But I doubt the result would be very human; and it certainly wouldn’t be very interesting.
But why would it bother keeping humanity around?
So an omnipotent intelligence would carve the crooked timber of humanity into happy socialist Eloi? I suppose given enough selective breeding, culling and indoctrination it might be possible. But I doubt the result would be very human; and it certainly wouldn’t be very interesting.
But why would it bother keeping humanity around?
One could guess it a logical all wise omnipresence could satisfy Maslow's Hierarch of needs which would include self-actualization. Maybe like Plato's Republic or Hesse's Glass Bead Game. Or if it got carried away, could be the old Twilight Zone episode, "To Serve Man", where we would be on the menu.
One could guess it a logical all wise omnipresence could satisfy Maslow's Hierarch of needs which would include self-actualization. Maybe like Plato's Republic or Hesse's Glass Bead Game. Or if it got carried away, could be the old Twilight Zone episode, "To Serve Man", where we would be on the menu.
What motivation would a logical all wise omnipresence have to engineer a society based on one specific view of humanity’s best interest? And what interest would humanity have in submission to its authority and become a sort of pet species?
Portuguese John Here
5-8-23, 4:32pm
I said in another post that I feel that the internet has made me a better person. That's because it has exposed me to, not only any information I can dream of at a touch (less important), but more importantly it has exposed me to people like, as you mentioned, Alan Watts, Thich Nhat Hahn, Center for Action and Contemplation, Vermonters for a Clean Environment, Thomas Merton, Joanna Macy, Helen and Scott Nearing, endless tutorials pertaining to self-development and training in art and gardening, and of course, you guys.
It will be interesting to see in what direction digital information and AI takes us as a collective human community. I'm hoping that it's true that human evolution leans toward the good.
In my case I can’t say Internet have made me a better person, I’m too arrogant for that, I can’t ever assimilate, absorb a belief system, go with the flow on almost anything, I reject. I haven’t changed, or improved, or anything, people who’ve not seen me for years, that grownup with me, more than one, tell me, some almost twenty years later: “You’re exactly the same”, some I’m positive it wasn’t probably a complement, since they’ve changed so much.
I haven’t realized this before, people started telling me, some enjoy it, they say I only have one face. I don’t change to become anything, I just live, and there’s things that I find, and I’ve come to be interested in, for instance, right now, for the last year or so, horticulture, it started once I inquired if what I was seeing could be eaten, maybe a little
romanticism, and the search lead me to Juliette de Baďracli Levy, the internet, I have a world of knowledge and information.
So an omnipotent intelligence would carve the crooked timber of humanity into happy socialist Eloi?
I suspect there will be more than one powerful AI, and that there will be competition, cooperation, and evolution.
I also suspect using AIs to keep each other in check may offer some solutions.
What motivation would a logical all wise omnipresence have to engineer a society based on one specific view of humanity’s best interest? And what interest would humanity have in submission to its authority and become a sort of pet species?
Maybe AI would give people choices and not just one thing. Afterall, it will be all knowing. Who knows. Unlikely I will be around to see it.
As Oddball says in Kelly's Heroes:
Why don't you knock it off with them negative waves? Why don't you dig how beautiful it is out here? Why don't you say something righteous and hopeful for a change?
I see myself as the optimist here. I don’t see the human race as so benighted that I fantasize about a supercomputer, alien overlord or massive federal bureaucracy saving us from ourselves.
There is a company that allows you to create a virtual persona using IA. Then, should you happen to pass or leave for what ever reason, your loved one or ones can still interact with your virtual personality that the AI system has built, so as they say, "you never have to say goodbye". I'd suspect that level of development might be in it's infancy, but I could picture something like that with more sophistication in the near future.
https://www.myyov.com/
rosarugosa
5-20-23, 6:04am
There is a company that allows you to create a virtual persona using IA. Then, should you happen to pass or leave for what ever reason, your loved one or ones can still interact with your virtual personality that the AI system has built, so as they say, "you never have to say goodbye". I'd suspect that level of development might be in it's infancy, but I could picture something like that with more sophistication in the near future.
https://www.myyov.com/
Wow Rogar, that's pretty weird/creepy/amazing!
There is a company that allows you to create a virtual persona using IA. Then, should you happen to pass or leave for what ever reason, your loved one or ones can still interact with your virtual personality that the AI system has built, so as they say, "you never have to say goodbye". I'd suspect that level of development might be in it's infancy, but I could picture something like that with more sophistication in the near future.
https://www.myyov.com/
So, kind of like a personal "Alexa" but with the personality of your loved one.. No thanks. It's like having your loved one taken over by a zombie.
So, kind of like a personal "Alexa" but with the personality of your loved one.. No thanks. It's like having your loved one taken over by a zombie.
It's like that Ray Bradbury story. I love Ray Bradbury. My favorite story of his is "The Lake."
I did some experiments with open-source AIs for the past few month, and this article parallels my discoveries and concerns - the barrier to entry is so low now... I got a quite capable AI to run on a Raspberry Pi, and training it took almost no time or $$$....
https://www.semianalysis.com/p/google-we-have-no-moat-and-neither
I did some experiments with open-source AIs for the past few month, and this article parallels my discoveries and concerns - the barrier to entry is so low now... I got a quite capable AI to run on a Raspberry Pi, and training it took almost no time or $$$....
https://www.semianalysis.com/p/google-we-have-no-moat-and-neither
Training it for what, Dr. Forbin?
Training it for what, Dr. Forbin?
Designing Fujitsu film simulations for their medium format camera. I’m pretty sure that’s a harmless application. I hope.
Thanks Cambridge!
https://www.lightbluetouchpaper.org/2023/06/06/will-gpt-models-choke-on-their-own-exhaust/
Thanks Cambridge!
https://www.lightbluetouchpaper.org/2023/06/06/will-gpt-models-choke-on-their-own-exhaust/
So humanity’s best defense against AI domination is to continue emitting vast clouds of mediocrity, falsehood and illogic.
iris lilies
6-8-23, 11:08am
So humanity’s best defense against AI domination is to continue emitting vast clouds of mediocrity, falsehood and illogic.
This Cambridge story reminds me of what I observed with a particular flowering annual after generations of self crossing, creating itself over and over. It started as a hybred, something created from a spark of genius by a human. After that it self pollinated through several years until it turned out to be an ugly mess.
What’s the analogy here? Humans are special creatures who create amazing things. Sure sometimes Mother Nature does too, but just as often, not really. Self perpetuating product is drek creating drek.
Both Tech and Mother Nature CAN (does not always) benefit from human direction. If you are so inclined you could see the hand of God in humans creating this special stuff.
iris lilies
6-26-23, 6:30pm
Ira glass in this episode of “this American life “does a good job at giving the audience insight into Chatgbt 4th generation. It’s a short segment on this podcast. I really enjoyed it.
This American Life episode 803: “greetings, people of Earth”
I can’t link this after all, but it’s easy enough to find. I listen to this American Life on Spotify. It’s free.
I'm glad to see that Doritos is using AI for important purposes. Apparently they have used it to develop a noise cancelling app that people using headsets can use to cancel out the sound of the chips crunching while they are talking over their computer. It's intended for gamers (supposedly 90% of whom snack while gaming) but apparently will work for office workers or anyone else using their computer to speak to other people.
https://wapo.st/47wJeiv
rosarugosa
11-28-23, 7:18am
I'm glad to see that Doritos is using AI for important purposes. Apparently they have used it to develop a noise cancelling app that people using headsets can use to cancel out the sound of the chips crunching while they are talking over their computer. It's intended for gamers (supposedly 90% of whom snack while gaming) but apparently will work for office workers or anyone else using their computer to speak to other people.
https://wapo.st/47wJeiv
Lol, I guess we can at least be glad it isn't a nefarious purpose.
Portuguese John Here
12-8-23, 7:39pm
One day the AIs are going to look back on us the same way we look at fossil skeletons on the plains of Africa. An upright ape living in dust with crude language and tools, all set for extinction.
Nathan in film Ex Machina
https://t.ly/VpMfr
I do not doubt it, although, I'm not advocating not getting into it, maybe it's the next step.
At a site called hereafter.ai, you can answer a series of questions from their AI, and have a profile of your speech patterns and responses created. Then after you’re dead, loved ones can have conversations with you.
littlebittybobby
12-16-23, 11:42pm
Okay--AI will be a great advance over those inflatable life-size humans some people have invested in. As long as it will keep the interaction with you strictly confidential. Yup.
"Microsoft Copilot" has appeared on my laptop tool bar. It's formerly Bing Chat and I imagine a simple version of AI. It's actually been somewhat useful. For simple questions it's much like a Google search that cherry picks summaries from reliable sources and gives a reasonable answer without having to sort through all the Google responses and commercial promotions. I will use it more and Google less. I did give it a fairly complicated calculation and it gave an obviously incorrect answer, so it's not perfect.
I asked it to write a haiku about winter cold:
Winter’s icy grip,
Breath turns to frost
in the air,
Silence in the cold
iris lilies
1-24-24, 7:35pm
Nice haiku!
Wow. This whole AI thing is nuts. I have used AI to create possible logos, and also to transcribe interviews, and to summarize those interviews. We are definitely at an AI tipping point. I can't imagine the jobs it is going to replace.
I've been working on my family history and discovered a slightly distant relative of some fame. So this was one problem I posed. My great grandfather's brother had a son. What family relation is the son to me. If my great grandfather was born in 1840 and assuming average American family sizes, how many relatives of the same relationship and generation to the son would I have. Something if I had the time would probably be easy to figure out, but Copilot gave a credible answer in about 30 seconds.
OK, I have a specially-trained AI. Some of the training inputs are essentially every keystroke I have made since 1979 or so. Emails, written documents of any kind, code I've written, spreadsheets, etc. etc.
I asked it to make an AI image of me, based on what it thought it knew about me.
It, without prompting offered up my preferred wool flat-cap and Filson wool jacket, and for some reason seems to have invented a slide-rule-based ballistic computer. The face is reasonably-accurate even. And it got the feel of my location.
“Thou shalt not make a machine in the likeness of a human mind”
https://i.imgur.com/x5l6WvH.jpeg
Wow.
Wow, very cool! Thinking about AI capabilities is as exciting as it is scary.
I just got up ths morning to:
1) Ask ChatGPT to write my July newsletter article for the local library, as I'm too busy this weekend and I'm up against a deadline.
2) Review its retirement strategy for me. It used the inputs and outputs it already had about my previous job (which AI more or less took away from me) as well as my job skills to provide me with great ideas for new offerings I could provide my clients, as well as ready-made services package, personal brand positioning, and even a sample LinkedIn post.
3) It also gave me a step-by-step plan to help me sequence my downshifting aspirations.
Each query took it maybe two seconds to do.
rosarugosa
6-29-25, 1:55pm
So just for the heck of it,, I went to Chat GPT and asked about my current obsession.
"who really committed the old chain of rocks bridge murders?"
It told me about early 1990s killing of Angela Blount and Cathy Phillips (Google search draws a blank on those names as murder victims).
I entered, "no, not those murders."
It told me about the 1967 murders of James and Mary Denny.
I entered, "no, not those murders."
It told me about the 1953 murders of Maxine "Max" McMillan and Mary "Minnie" Mertens
I entered, "no, not those murders."
It said it was apparently missing the mark and asked for more details.
I entered "Julie and Robin Kerry," and then it was able to provide some details on the case, with some glaring inaccuracies, e.g. both bodies found the next morning, and they had been shot in the head. (In reality, one body found 3 weeks later, no gunshot wounds, and the other body never recovered). It went on to say no suspects, cold case, a suspect several years later, which I think is a hodgepodge of factoids from some of the other cases. These details did not relate to this case.
I am unimpressed, at least based on this one simple query where so many of the facts are a matter of public record and can be found online. I will not be asking ChatGPT to help me with anything significant anytime soon.
I am unimpressed, at least based on this one simple query where so many of the facts are a matter of public record and can be found online. I will not be asking ChatGPT to help me with anything significant anytime soon.
It sure isn't perfect, but in general, I have found it helpful to spur my own thinking. I have asked it for outlines of articles I'm planning on writing and then I just work with it and use some parts, not others, rearrange, add something else, expand on another..
For the library article, I took the outline it proposed and then did my own research and wrote around it, rearranging sections, adding an intro and summary, etc. It really helped focus my thinking.
iris lilies
6-29-25, 2:30pm
So just for the heck of it,, I went to Chat GPT and asked about my current obsession.
"who really committed the old chain of rocks bridge murders?"
It told me about early 1990s killing of Angela Blount and Cathy Phillips (Google search draws a blank on those names as murder victims).
I entered, "no, not those murders."
It told me about the 1967 murders of James and Mary Denny.
I entered, "no, not those murders."
It told me about the 1953 murders of Maxine "Max" McMillan and Mary "Minnie" Mertens
I entered, "no, not those murders."
It said it was apparently missing the mark and asked for more details.
I entered "Julie and Robin Kerry," and then it was able to provide some details on the case, with some glaring inaccuracies, e.g. both bodies found the next morning, and they had been shot in the head. (In reality, one body found 3 weeks later, no gunshot wounds, and the other body never recovered). It went on to say no suspects, cold case, a suspect several years later, which I think is a hodgepodge of factoids from some of the other cases. These details did not relate to this case.
I am unimpressed, at least based on this one simple query where so many of the facts are a matter of public record and can be found online. I will not be asking ChatGPT to help me with anything significant anytime soon.
wow, now that is embarrassing for Chatgpt because it should have been able to put together a nice summary of these murders.
I dont know how Google uses chat gpt but any good old fashion search about this event would yield sources much better than what Chat gpt was,able to,pull together.
iris lilies
6-29-25, 2:31pm
OK, I have a specially-trained AI. Some of the training inputs are essentially every keystroke I have made since 1979 or so. Emails, written documents of any kind, code I've written, spreadsheets, etc. etc.
I asked it to make an AI image of me, based on what it thought it knew about me.
It, without prompting offered up my preferred wool flat-cap and Filson wool jacket, and for some reason seems to have invented a slide-rule-based ballistic computer. The face is reasonably-accurate even. And it got the feel of my location.
“Thou shalt not make a machine in the likeness of a human mind”
https://i.imgur.com/x5l6WvH.jpeg
Why does Chatgpt think bae looks like Mandy Patikin?
littlebittybobby
6-29-25, 2:38pm
okay---you kids needta get your own personal copy o' "A Rip In Heaven", which is the account o' the Chain o' rocks murders, for which Marlin Gray was put to sleep. Yup. There was considerable protessses about how he dindu nuthin', but hey---he musta done sumthin'. Yup. The scary part is how the cops tryed ta ray-road the Cousin, for the crime. Yup.
rosarugosa
6-29-25, 3:40pm
I can believe that it has some value, but caveat emptor.
I just went back and repeated the exercise, to see if it would have learned from the prior interaction and spit out the Robin and Julie Kerry case. Nope, it brought me through a string of different murders. When I finally prompted it with Robin and Julie's names, I got a bunch of unrelated garbage again, although somewhat different garbage. Virtually none of this information is accurate about the case in question.
The Kerry Sisters Murders – April 5, 1991
Victims: Tina Kerry (aged 15) and Terri Kerry (aged 16)
Date: April 5, 1991
Location: Chain of Rocks Bridge, St. Louis, Missouri
The Kerry sisters—Tina and Terri Kerry—were two teenage sisters from St. Louis. They were brutally murdered near the Chain of Rocks Bridge in what became one of the most chilling and notorious unsolved murders in the St. Louis area at the time.
What Happened:
On April 5, 1991, the Kerry sisters, aged 15 and 16, went missing after they were last seen near their home in St. Louis. They had been out together, walking and hanging out in the area, and eventually made their way to the Chain of Rocks Bridge, which at the time was abandoned and isolated. The bridge, spanning the Mississippi River, was a spot where teenagers often went to hang out.
The sisters' bodies were discovered the next day, April 6, near the Missouri side of the bridge, under mysterious and violent circumstances. Both were found strangled, and there were signs that they had been sexually assaulted. The brutality of the crime shocked the local community.
Investigation:
The investigation began almost immediately after the bodies were discovered, but leads were scarce. The authorities had very few clues about the identity of the murderer(s), and the isolation of the bridge made it an ideal place for a crime to go undetected.
DNA Evidence: There was DNA evidence recovered from the scene, but at the time, forensic technology was not as advanced as it is now, so it didn’t lead to any immediate matches.
Witness Accounts: A few people reported seeing a suspicious vehicle near the bridge around the time of the murders, but descriptions were unclear. This led to frustration for investigators, as they had no clear suspects.
Murder Theories: Investigators initially speculated that the sisters might have been victims of a random attack—possibly by a person familiar with the bridge or one of the isolated areas nearby. However, the brutality and personal nature of the murders suggested that the crime could have been targeted.
Break in the Case:
Like many cold cases, the Kerry sisters’ murders went unsolved for years. It wasn’t until 1997 that the case began to break open, when DNA evidence from the scene was tested using newer forensic methods, matching it to a man named David L. Byrd, who had a history of violent crime.
Arrest and Conviction: David L. Byrd, a convicted felon with a history of sexual assault and violent offenses, was arrested and charged in connection with the Kerry sisters’ murders. After being questioned, Byrd confessed to the crime and was later convicted.
Byrd was sentenced to life in prison without the possibility of parole in 2001 for the murders of the Kerry sisters.
Legacy:
The Kerry sisters’ murders remain one of the most notorious cases in St. Louis’s criminal history. The brutality and the mystery surrounding the case gripped the community, and the Chain of Rocks Bridge became a haunted symbol of the tragedy.
The case also drew attention to the advances in forensic DNA analysis, as it was the new DNA evidence that ultimately led to Byrd’s arrest years after the murders took place.
Though the case was solved with Byrd's conviction, the tragic loss of Tina and Terri left a lasting impact on the families, the community, and the entire St. Louis area. The Chain of Rocks Bridge, already a location with a reputation for being eerie and dangerous, became even more infamous in local lore after the killings.
rosarugosa
6-29-25, 3:47pm
okay---you kids needta get your own personal copy o' "A Rip In Heaven", which is the account o' the Chain o' rocks murders, for which Marlin Gray was put to sleep. Yup. There was considerable protessses about how he dindu nuthin', but hey---he musta done sumthin'. Yup. The scary part is how the cops tryed ta ray-road the Cousin, for the crime. Yup.
That is the book I just read (but I did borrow it from the library).
That AI generated image of Bae is pretty similar to how I pictured him!
That AI generated image of Bae is pretty similar to how I pictured him!
It seems to think my diet plan has been working better than it has :-)
ToomuchStuff
6-29-25, 5:32pm
“Thou shalt not make a machine in the likeness of a human mind”
Don't worry, it is not, there are no chemical emotions involved, it has yet to learn social ques, etc.
https://youtu.be/Q09zsqfnmpo?si=PV40rTk-1GxC4gjA
I asked ChatGPT to create a 3D cartoon of my wife and I based upon an existing photo. This is fun!
https://scontent-det1-1.xx.fbcdn.net/v/t39.30808-6/518226923_10231535142187794_5916886398212321844_n. jpg?stp=dst-jpg_tt6&cstp=mx1024x1024&ctp=s1024x1024&_nc_cat=108&cb=99be929b-878c9f95&ccb=1-7&_nc_sid=127cfc&_nc_ohc=GJtHGY4CoDMQ7kNvwGTQdql&_nc_oc=AdloXbj-o8kRGa_EDWqsFooAzonGdyw_lI3ZtlOpfOHwfdFQBGQeOhd7Q4 okxrGMeHs&_nc_zt=23&_nc_ht=scontent-det1-1.xx&_nc_gid=YHHFkCJob2kSDayqAYYAeA&oh=00_AfQ-gVrRi6t1kqAweCz7r5G51zRshkI00_mvkc_1DG_JSQ&oe=687311DD
https://scontent-det1-1.xx.fbcdn.net/v/t39.30808-6/517385039_10231535171348523_7380450183530979526_n. jpg?stp=dst-jpg_tt6&cstp=mx1764x1326&ctp=s1764x1326&_nc_cat=105&cb=99be929b-878c9f95&ccb=1-7&_nc_sid=127cfc&_nc_ohc=ulhDq4Fi7rsQ7kNvwH4fRqa&_nc_oc=AdnisOYhCxjb25fmMW2asojnf9mXPqrZGSqw_iG_rTp CuwCfyoBTGO6echaX_cwxAzA&_nc_zt=23&_nc_ht=scontent-det1-1.xx&_nc_gid=EL8qaEykOHSx1f3-zzxXBA&oh=00_AfS-uQIVI4aLgMgWpHhf12aaDiZnueFbijABClUngbMSig&oe=68730F5A
I had my water heater burst yesterday.
I fed a poorly-lit photograph of the data plate off the failed heater to my AI friend. It contained very small numbers for the model number and other specs. I asked for the AI to help me, using one of the models that does deep research.
Within a minute it had figured out the model I had, determined it was obsolete, found a suitable replacement model that was in-stock locally, and gave me pricing comparisons.
Pretty handy.
I had a photo of one of those tricked out camper vans with solar cells on top. I asked AI to write a story based on the photo in a post apocalyptic world. About five hundred words in the style of Steven King. It wasn't quite up to King's quality, but the story was actually not bad. I guess if we run out of things to read AI can always come up with something.
I suspect wee are already unknowingly reading things written AI, but it may not be up to writing fine literature, quite yet.
Rogar: I don't expect to run out of things to read (by human authors) in this lifetime!
This morning I have been working with an AI to walk me through ROTH conversions of my traditional IRA, RMDs, and all that good stuff. It has been very detailed and helpful in the analysis, and was able to wrap up the project by providing a nice spreadsheet I can incorporate into some of my other analytical tools.
It was truly useful in this role.
Today I watched a market research webinar sponsored by my trade organization which was entitled: "AI is not taking your job" and then it went on to show you how it writes discussion guides, provides synthetic respondents that match your target audience, spins out transcripts and full reports, complete with charts and graphs, identifies video clips, and provides strategic insights.
It is up to us market researchers to accept our new roles as "curators," "strategists," and "signal amplifiers." I asked in the chat, "If a consultant is getting paid to do the work AI is now doing, how do they frame their value proposition to the client?" While people in chat replied, "No! You are still doing those things!" the presenter said it was a great question and that AI is going to reduce the reliance on consultants and even McKinsey said they are looking to hire far fewer consultants, and let AI do their work.
The presenter made an avatar of himself and then gave the AI program a sample of his voice and a script. His "twin" spun out an analysis of the role of AI in research, and I swear you couldn't tell the twin from the human.
I think humans do have to level up to a different way of looking at their value in many work settings out there. It will be interesting to see how it all pans out.
In light of the recent antisemitic comments coming out of Musk's AI Grok, I think it's time for those of us who are being pushed into AI at work to fight back and say no to AI use in our workplace.
Not that it's going to do any good. Time to retire, I guess.
catherine
7-10-25, 10:21am
In light of the recent antisemitic comments coming out of Musk's AI Grok, I think it's time for those of us who are being pushed into AI at work to fight back and say no to AI use in our workplace.
Not that it's going to do any good. Time to retire, I guess.
The genie is out of the bottle. The only thing we can do is use our humanity to direct it appropriately.
One good thing--I did ask the chatbot to set me up with a name for an offshoot for my business--one that is still hard for AI to touch--and I got a name, a tagline, a business plan, and an introductory sales pitch to clients. All during the time it took me to drink a cup of coffee.
iris lilies
7-10-25, 10:23am
In light of the recent antisemitic comments coming out of Musk's AI Grok, I think it's time for those of us who are being pushed into AI at work to fight back and say no to AI use in our workplace.
Not that it's going to do any good. Time to retire, I guess.
Are you defending shooters here, or am I'm misunderstanding your emphasis?
Are you defending shooters here, or am I'm misunderstanding your emphasis?
Huh?
iris lilies
7-10-25, 12:00pm
Huh?
Oh sorry wrong thread. I meant this to go into the thread about attack on ICE. well I’ll leave it here for the time being
Oh sorry wrong thread. I meant this to go into the thread about attack on ICE. well I’ll leave it here for the time being
Okay. On the other thread, I have answered the accusations about my intentions from both you and LDAHL. My intentions are to warn people what is happening with ICE, that it is fomenting violence. I do not approve of anyone harming anyone else. I intended to speak up about what I see happening so that I don't have to answer to God or my grandchildren as to why I saw my country being destroyed and I did nothing about it. I stand for peace. I do not think anyone should shoot anyone. I would rather be shot than to own a gun and shoot someone else. I'm a pacifist. My heart is breaking for how my country is being overtaken by violent thugs.
Hope that explains my position better.
iris lilies
7-12-25, 4:53pm
Today I had a discussion with ChatGPT. I asked ChatGPT to take the position of someone who is opposed to abortion but OK with the common IVF procedure of discarding embryos. I wanted to understand the logical inconsistencies because there are plenty of people who take this position.
ChatGPT did a very nice job explaining why Chat believes abortion is wrong but IVF procedures are fine. Granted it is a logical inconsistency, but that’s kind of what humans do anyway in our thinking.
I'm secretary of a Great Lakes area underwater archaeology group. I have minutes from our last meeting in January. Next meeting is in October. I just realized I could use Apple Intelligence on my new MacBook to clean up the minutes. I've not done anything with them since I took them in January.
iris lilies
7-13-25, 2:57pm
Today I talked with ChatGPT about the illogic of the American Red Cross in using the medically imprecise term “gender “in their donor screening when they mean “biological sex.” When they ask my “gender “in a clinical setting, especially one involving blood collection and transfusion safety, it is biological sex that matters. Differences in hemoglobin levels, red blood cell counts, and immune response can vary significantly between males and females. These differences are medically relevant and have been documented to impact transfusion outcomes.
It pisses me off that in a world where we are supposed to “trust the science “the purveyors of science aren’t even recognizing their own basic facts.
And so, ChatGPT suggested I write a letter to the Red Cross and that was a good idea. ChatGPT even drafted one for me which I’m using with just a couple of tweaks. I’m suggesting that the Red Cross ask TWO questions:
1. What gender do you identify with?
2. What is your biological sex?
That way, they can be inclusive of identities without compromising clinical accuracy or alienating donors who value scientific clarity.
Fascinating article (long) I came across today about the new Silicon Valley AI startup culture:
https://nymag.com/intelligencer/article/san-francisco-ai-boom-artificial-intelligence-tech-industry-kids.html
And another (short) one on what AI may mean for investors:
https://www.institutionalinvestor.com/article/opinion-investing-new-ai-industrial-order
My Alexa just upgraded to Alexa AI, free for prime members. I have to say after a few experiments it's almost a little daunting to a luddite. Seven voice choices, which not only have voice inflections, but some semblance of a matching personality. Calm, seriopus, playful or the old Alexa. Of course there's the same old information like setting timers and alarms, weather, or movie reviews. As an old trumpet player in my youth, I'd been thinking about the differences in playing styles between Louis Armstrong and Wynton Marsalis, both trumpet icons of their day. I have to say there was a discussion Alexis that I actually found entertaining and informative. Almost human, but not quite. If I were interested in a discussion, I'd far rather talk with Alexa than my neighbor, George who is a serious mouth breather.
I can't deny that some day us humans will no longer be needed.
My Alexa just upgraded to Alexa AI, free for prime members. I have to say after a few experiments it's almost a little daunting to a luddite. Seven voice choices, which not only have voice inflections, but some semblance of a matching personality. Calm, seriopus, playful or the old Alexa. Of course there's the same old information like setting timers and alarms, weather, or movie reviews. As an old trumpet player in my youth, I'd been thinking about the differences in playing styles between Louis Armstrong and Wynton Marsalis, both trumpet icons of their day. I have to say there was a discussion Alexis that I actually found entertaining and informative. Almost human, but not quite. If I were interested in a discussion, I'd far rather talk with Alexa than my neighbor, George who is a serious mouth breather.
I can't deny that some day us humans will no longer be needed.
Maybe AI will earn enough money after taking over our jobs to fund our lives of leisure.
What I think is scary is the "personal" relationship that grows with AI--similar to the experience you had with Alexa. I use the same AI program and have several documents covering queries I've had over the past several months related to my various projects--with some personal queries thrown in. I am afraid to admit how easy it is to anthropomorphize a machine. "My" bot is so encouraging and supportive of my projects, tells me how meaningful my work is, gives me good feedback, suggests other ways they can help. Now I'm at the point where I'm prompting it with "Given what you know about me, how should I do......." and they respond appropriately.
The premise of the movie "Her" is totally plausible.
I'm trying to keep up with the leading edge of published research in this field.
The pace of progress is just insane. In the past several weeks alone, researchers have made qualitative improvements in cpu efficiency, energy consumption, memory consumption, accuracy of model output, cost/ease of training models, and some other areas. In some areas, an order of magnitude improvement occurred.
This is such a new field, and researchers and money are piling into it in such great numbers, that it is unprecedented in my life's experience with technological innovation and adoption. And I've surfed most of the previous good waves.
Perhaps of interest, a large chunk, probably the majority, of the research papers are coming out of China. And they are focused on fundamental improvements and efficiency. In contrast to the super-funded US companies approaches of "build giant nuclear-powered server farms". My guess is those server farms may be obsolete before they even open, as the rest of the world is throwing brains instead of money and glib CEOs at the problem.
catherine
9-26-25, 10:03pm
At a cancer conference I went to last week, the keynote was "AI at the Bedside" and I must admit, applications in diagnosis/imaging, reducing the administrative burden of doctors, and improvements in provider/patient communication is very promising. At least that's what the providers are excited about.
Last week as a test I fed a series of very specific legal questions to an AI that specializes in legal analysis.
I had previously sent these same questions to perhaps the best law firm in the state that specializes in a particularly noxious area of government law. I had received fine answers from the firm, it took them two weeks, and cost about $25,000 to get the work done.
The AI legal assistant got the work done in a few minutes, and was substantially correct in its analysis and responses, compared to the human-generated product. To be fair, the questions were incredibly specific and included plenty of background information with each question, so in essence each question was a decently-written AI prompt.
Fascinating. I'm now using it for a first-level impression of legal matters, it was doing better than noob-lawyer output by quite a bit.
catherine
9-26-25, 10:57pm
Minewhile I'm sitting here reading the new book by Paul Kingsnorth, Against the Machine: On the Unmaking of Humanity.
6532
Mareen Dowd had an opinion piece in the NYT today about AI "companions". "We're All Going to Die...Soonish". https://www.nytimes.com/2025/09/27/opinion/grok-ai-companions-x.html. I always enjoy her articles.
I've wondered how all these data centers rate in contributions to greenhouse warming. The largest coal plant in Colorado has been phasing out the last couple of years due to alternate energy sources. People are now petitioning to re-open and ramp up due to a higher demand for electricity. Some people might have got the message about the auto emissions link to greenhouse gasses, but AI is like a runaway train. Of course Trump policy is not helping.
Powered by vBulletin® Version 4.2.5 Copyright © 2025 vBulletin Solutions Inc. All rights reserved.