That is why may experts are asking for greater transparency and to establish standards. The programmers of the large language models don't understand how what they did results in the AI that is their product. That can't be good.
ChatGPT on Audiophile
- Thread starter Kingrex
- Start date
me too.
We are only starting to understand the effects of social media, especially on young folks and in countries other than the U.S. We release this stuff thinking it will be beneficial, and it is, but like any tool it must be maintained. Who does that and how? The profit motive complicates how much time and effort is put into preventing misuse.
Perhaps I should just surrender to the inevitable. Perhaps what I desperately need is an AI to select music, listen to it and tell me how I'm feeling.
Fortunately some people used AI to create detectors of ChatGPT. IMO including watermarks in ChatGPT responses should be mandatory. The cost of adapting our behavior to face such AI tools will be very high.
It's an interesting issue, intellectually and culturally and for the masses, still in its infancy. The old rule about "garbage in/garbage out" applies here, but isn't just limited to crappy sources, incorrect information, or the kludginess of what we think of as the 'AI' controlling it. I've experimented with it on various subjects and have also had to confront whether to allow it in post-grad level courses. (I don't condone it).
I'm not down on any tool. There is a process to the assembly of known information that depends not only on content but organization. And then there's the content itself.
What if, hypothetically, a system could freely tap into any database available (leaving aside the legal, privacy and other issues?). I'm not sure the resulting output would improve in substance though it may have much more breadth and depth. And while we are on that subject, much in science and progress keeps moving so what was "current" a few weeks ago may be wrong or misleading. Think "paradigm" theory and how slowly established models in many areas, professions, etc. are slow to respond to change.
But, I guess I have some even more fundamental questions:
what are the limits on "intake" because the foundational materials are going to determine a lot;
To what extent is the selection of ingested material simply a machine process, and assuming so, what are its criteria for selection? (Assume that the legal permissions aren't an issue, is there a ranking of trusted sources by priority for every topic- I suspect that has to be built out more. Are there any inherent biases in such selection?
My experience in doing in-depth research and writing tells me there is a human element to judgment that is irreplaceable. But that is the question, isn't it? I'm not sure the "Turing Test" is revealing enough. You could, theoretically, clean up the resultant specific output sufficiently that it mimics human writing and thought and still not be much beyond rote regurgitation. I think the Google dudes are way ahead, as are some of the deep thing tanks. I'm not a conspiracy theorist, I regard the Terminator as entertainment and am fascinated by the whole thing.
I have done a few side projects involving the use of motion picture and audio imagery of old dead actors for the purpose of placing them in new fields. The legal issues alone are daunting (although nicely addressed several decades ago, before the technology was viable). But even if that matured, it is an illusion.
Maybe everything we read, watch and "intake" is just that- an illusion, a "take" and at best, a snapshot in time. Things seem to be moving faster in life- not just computers, AI, technology or culture. Everything is moving faster. Are human brains capable of grasping the implications of what they do? That's a question I can't answer here without more thought, and some concern over history, politics and power, something that I have no interest in discussing in a provocative manner.
Call me a semi-informed, interested bystander.
I'm not down on any tool. There is a process to the assembly of known information that depends not only on content but organization. And then there's the content itself.
What if, hypothetically, a system could freely tap into any database available (leaving aside the legal, privacy and other issues?). I'm not sure the resulting output would improve in substance though it may have much more breadth and depth. And while we are on that subject, much in science and progress keeps moving so what was "current" a few weeks ago may be wrong or misleading. Think "paradigm" theory and how slowly established models in many areas, professions, etc. are slow to respond to change.
But, I guess I have some even more fundamental questions:
what are the limits on "intake" because the foundational materials are going to determine a lot;
To what extent is the selection of ingested material simply a machine process, and assuming so, what are its criteria for selection? (Assume that the legal permissions aren't an issue, is there a ranking of trusted sources by priority for every topic- I suspect that has to be built out more. Are there any inherent biases in such selection?
My experience in doing in-depth research and writing tells me there is a human element to judgment that is irreplaceable. But that is the question, isn't it? I'm not sure the "Turing Test" is revealing enough. You could, theoretically, clean up the resultant specific output sufficiently that it mimics human writing and thought and still not be much beyond rote regurgitation. I think the Google dudes are way ahead, as are some of the deep thing tanks. I'm not a conspiracy theorist, I regard the Terminator as entertainment and am fascinated by the whole thing.
I have done a few side projects involving the use of motion picture and audio imagery of old dead actors for the purpose of placing them in new fields. The legal issues alone are daunting (although nicely addressed several decades ago, before the technology was viable). But even if that matured, it is an illusion.
Maybe everything we read, watch and "intake" is just that- an illusion, a "take" and at best, a snapshot in time. Things seem to be moving faster in life- not just computers, AI, technology or culture. Everything is moving faster. Are human brains capable of grasping the implications of what they do? That's a question I can't answer here without more thought, and some concern over history, politics and power, something that I have no interest in discussing in a provocative manner.
Call me a semi-informed, interested bystander.
Last edited:
What a canned response. Its high quality and needs a high quality amp? Why didn't it specify the speakers electrical characteristics as a way to match an amp. A serious deficiency in the answer.
And then it goes onto fan the fire of SS vs Tube. I guess AI does not think SS amps are warm and natural. Of that tube amps can control drivers.
Not bad for Chat gpt this advice , i think it does a better job than a lot of reviewers.
Another option to consider is a tube amplifier. Tube amplifiers can provide a warm and natural sound that complements the Wilson Chronosonic XVX's detailed and nuanced performance. Some recommended tube amplifiers for the Wilson Chronosonic XVX include the following:
Another option to consider is a tube amplifier. Tube amplifiers can provide a warm and natural sound that complements the Wilson Chronosonic XVX's detailed and nuanced performance. Some recommended tube amplifiers for the Wilson Chronosonic XVX include the following:
- Audio Research Reference 160M
- VTL S-400 Series II
- McIntosh MC2301
- Jadis JA800
- PrimaLuna EVO 400
Lol , Chat Gpt has a sense of humour.
Can somebody type in what Chat Gpt thinks regarding High end audio cables
Why not the VTL Siegfried II?
The main problem of the ChatGPT answers is that they are well formulated and plausible. This answer could easily go as an advice from an WBF member ... The bot knows audiophiles love to recommend lists of equipment and even more dangerous, knows how to use the word natural!
Price i reckon .
But for a newcomer to audio i think the tube advice was pretty good .
The solidstate advice looks to be curtained to a certain budget as well .
Unless you are JAY / audiolab , he runs his XVX with Pass labs , but i dont know if he thinks its the ultimate amplification
I was joking - I own the Siegfried II and you know audiophiles love to see their gear recommended, even by a bot!
But perhaps Chat Gpt can recommend some speakers for the Lamm ML3 ...
From NY Time article:
I first met Sam Altman [chatGPT kingpin] in the summer of 2019, days after Microsoft agreed to invest $1 billion in his three-year-old start-up, OpenAI.
...
As if he were chatting about tomorrow’s weather forecast, he said the U.S. effort to build an atomic bomb during the Second World War had been a “project on the scale of OpenAI — the level of ambition we aspire to.”
...
Some believe it will deliver a utopia where everyone has all the time and money ever needed. Others believe it could destroy humanity. Still others spend much of their time arguing that the technology is never as powerful as everyone says it is, insisting that neither nirvana nor doomsday is as close as it might seem.
Mr. Altman, a slim, boyish-looking, 37-year-old entrepreneur and investor from the suburbs of St. Louis, sits calmly in the middle of it all.
...
“He has a natural ability to talk people into things,” Mr. Graham said. “If it isn’t inborn, it was at least fully developed before he was 20. I first met Sam when he was 19, and I remember thinking at the time: ‘So this is what Bill Gates must have been like.’”
...
Mr. Altman is not a coder or an engineer or an A.I. researcher. He is the person who sets the agenda, puts the teams together and strikes the deals.
...
he holds no stake in OpenAI. The only money he stands to make from the company is a yearly salary of around $65,000 — “whatever the minimum for health insurance is,” he said — and a tiny slice of an old investment in the company by Y Combinator.
His longtime mentor, Paul Graham, founder of Y Combinator, explained Mr. Altman’s motivation like this:
“Why is he working on something that won’t make him richer? One answer is that lots of people do that once they have enough money, which Sam probably does. The other is that he likes power.”
...
His grand idea is that OpenAI will capture much of the world’s wealth through the creation of A.G.I. and then redistribute this wealth to the people. In Napa, as we sat chatting beside the lake at the heart of his ranch, he tossed out several figures — $100 billion, $1 trillion, $100 trillion.
I respond to this article this way: Humans, do you want to put your fate in the hands of this talented businessman? 37 is a great age, but one does learn as one gets older. That learning takes place by making mistakes, of course.
Gosh, I hope he decides to redistribute some wealth to me. Previously, my new priority was to become a friend of Elon so I could live on Mars. I have a new priority. Sam is the man.
I first met Sam Altman [chatGPT kingpin] in the summer of 2019, days after Microsoft agreed to invest $1 billion in his three-year-old start-up, OpenAI.
...
As if he were chatting about tomorrow’s weather forecast, he said the U.S. effort to build an atomic bomb during the Second World War had been a “project on the scale of OpenAI — the level of ambition we aspire to.”
...
Some believe it will deliver a utopia where everyone has all the time and money ever needed. Others believe it could destroy humanity. Still others spend much of their time arguing that the technology is never as powerful as everyone says it is, insisting that neither nirvana nor doomsday is as close as it might seem.
Mr. Altman, a slim, boyish-looking, 37-year-old entrepreneur and investor from the suburbs of St. Louis, sits calmly in the middle of it all.
...
“He has a natural ability to talk people into things,” Mr. Graham said. “If it isn’t inborn, it was at least fully developed before he was 20. I first met Sam when he was 19, and I remember thinking at the time: ‘So this is what Bill Gates must have been like.’”
...
Mr. Altman is not a coder or an engineer or an A.I. researcher. He is the person who sets the agenda, puts the teams together and strikes the deals.
...
he holds no stake in OpenAI. The only money he stands to make from the company is a yearly salary of around $65,000 — “whatever the minimum for health insurance is,” he said — and a tiny slice of an old investment in the company by Y Combinator.
His longtime mentor, Paul Graham, founder of Y Combinator, explained Mr. Altman’s motivation like this:
“Why is he working on something that won’t make him richer? One answer is that lots of people do that once they have enough money, which Sam probably does. The other is that he likes power.”
...
His grand idea is that OpenAI will capture much of the world’s wealth through the creation of A.G.I. and then redistribute this wealth to the people. In Napa, as we sat chatting beside the lake at the heart of his ranch, he tossed out several figures — $100 billion, $1 trillion, $100 trillion.
I respond to this article this way: Humans, do you want to put your fate in the hands of this talented businessman? 37 is a great age, but one does learn as one gets older. That learning takes place by making mistakes, of course.
Gosh, I hope he decides to redistribute some wealth to me. Previously, my new priority was to become a friend of Elon so I could live on Mars. I have a new priority. Sam is the man.
140 watts continuous from 20Hz to 20kHz.
Tetrode = 300 watts
300 watts
400 watts
In Mono Ultra-linear, 140 watts.
Seems these amps have sufficient power , it didnt recommend low power tubes
I started a ChatGTP account.
Question: How do vintage loudspeakers sound?
Answer:
Vintage loudspeakers can have a unique sound that is different from modern speakers. Many people appreciate the sound of vintage loudspeakers because they have a warm, rich, and full-bodied sound that some feel is lacking in modern speakers. However, it's important to keep in mind that not all vintage speakers are created equal and that sound quality can vary greatly depending on the make and model.
Some vintage speakers were designed with specific musical genres in mind and can excel in reproducing certain types of music. For example, some vintage speakers were designed for jazz or classical music, while others were designed for rock or electronic music. It's also worth noting that vintage speakers may have some technical limitations compared to modern speakers, such as lower power handling or less accurate frequency response.
Ultimately, the sound of vintage loudspeakers is a matter of personal preference, and what sounds great to one person may not be appealing to another. If you're interested in purchasing vintage speakers, it's a good idea to do some research on the specific make and model and try to listen to them before making a purchase decision.
Question: How do vintage loudspeakers sound?
Answer:
Vintage loudspeakers can have a unique sound that is different from modern speakers. Many people appreciate the sound of vintage loudspeakers because they have a warm, rich, and full-bodied sound that some feel is lacking in modern speakers. However, it's important to keep in mind that not all vintage speakers are created equal and that sound quality can vary greatly depending on the make and model.
Some vintage speakers were designed with specific musical genres in mind and can excel in reproducing certain types of music. For example, some vintage speakers were designed for jazz or classical music, while others were designed for rock or electronic music. It's also worth noting that vintage speakers may have some technical limitations compared to modern speakers, such as lower power handling or less accurate frequency response.
Ultimately, the sound of vintage loudspeakers is a matter of personal preference, and what sounds great to one person may not be appealing to another. If you're interested in purchasing vintage speakers, it's a good idea to do some research on the specific make and model and try to listen to them before making a purchase decision.
Last edited:
Similar threads
- Sticky
 | Steve Williams Site Founder | Site Owner | Administrator |  | Ron Resnick Site Co-Owner | Administrator |  | Julian (The Fixer) Website Build | Marketing Managersing |