• Welcome to ASR. There are many reviews of audio hardware and expert members to help answer your questions. Click here to have your audio equipment measured for free!

GENERIC "I ASKED AI [SOMETHING ABOUT AUDIO]- WHAT DO YOU THINK?" THREAD

Status
Not open for further replies.
I've only measured two 70s loudspeakers systems and they were both brighter having tweeter levels higher than most modern measurements I've seen or designed myself. Another reason could be speaker placement. In the 70s speakers were often placed on the floor so they needed a bit more tweeter level.
 
With all due respect, but what is the point
a) of asking questions like this to the automatic bullshitgenerators;
b) publishing the logs of these interactions on a forum
?

EXACTLY!!!!!!!!!!!!!!

AI has its uses. For example, ask Claude a question like, "what does minimum phase mean in context of audio DSP" and you get a very good answer. The key to asking questions is to be specific about the query and agnostic about your position. As multiple posters have pointed out, asking an AI leading questions will make the AI give you an answer you want to hear.

Although having said that, I asked Claude:

1738333576778.png


Well done Claude! Well done!! *applause*

(EDIT): Microsoft Copilot ... not so great.

1738346710454.png
 
Last edited:
I guess you get what you want from AI. It's still interesting, or entertaining to make these queries
That doesn't mean it's interesting or entertaining to share them...
 
Nice analogy: both are responsible for immeasurably massive environmental destruction. But at least a Model T got people somewhere…
Not unlike the manufacturing process and transportation to produce your favorite audio gear...
 
Nice analogy: both are responsible for immeasurably massive environmental destruction. But at least a Model T got people somewhere…
That's borderline blunt -actually, no, it is blunt.

The Model T changed the car industry by introducing mass production, especially the assembly line. This made building cars much cheaper, so more people could afford them, not just the wealthy. It helped make personal transportation a reality for everyday folks.

It also pushed manufacturing, engineering, and materials forward, influencing how things were built in many industries. The Model T didn’t just transform transportation; it changed how society and the economy worked in a big way.
 
That's borderline blunt -actually, no, it is blunt.

The Model T changed the car industry by introducing mass production, especially the assembly line. This made building cars much cheaper, so more people could afford them, not just the wealthy. It helped make personal transportation a reality for everyday folks.

It also pushed manufacturing, engineering, and materials forward, influencing how things were built in many industries. The Model T didn’t just transform transportation; it changed how society and the economy worked in a big way.
Agreed. But nothing you wrote contradicts what I wrote. The the amount of energy and water used by AI is staggering, especially when you consider it is actually mostly useless.
 
Last edited by a moderator:
Let's stay away from climate matters please folks .
 
Agreed. But nothing you wrote contradicts what I wrote. The the amount of energy and water used by AI is staggering, especially when you consider it is actually mostly useless.

AI offers huge productivity gains to software developers and will even replace lots of developers all togheter. AI helps teachers with the preparation of courses. AI helps with content creation (graphic design and writing texts). AI chatbots help customers with FAQ's. Just some examples I have experience with, other people probably know of similar examples in other domains (like AI used for driver assistance in cars, AI used in stock trading...).

When experts say that AI could do 80% of jobs in the very near future, it's safe to conclude it's capable of doing something useful. If we're not careful, AI and robots will conclude people are the weak link.
 
Last edited:
For goodness sake, NO POLITICS!
 
AI offers huge productivity gains to software developers and will even replace lots of developers all togheter. AI helps teachers with the preparation of courses. AI helps with content creation (graphic design and writing texts). AI chatbots help customers with FAQ's. Just some examples I have experience with, other people probably know of similar examples in other domains (like AI used for driver assistance in cars, AI used in stock trading...).

When experts say that AI could do 80% of jobs in the very near future, it's safe to conclude it's capable of doing something useful. If we're not careful, AI and robots will conclude people are the weak link.
Regarding that last part, I remember hearing a podcast where Elon Musk was interviewed. Based on what he said, the future could take a dark turn if we’re not careful. Regardless of one's opinion of him, and despite how much he puts out there, one thing he certainly isn’t is stupid. If someone like him says something like that, I think it’s worth paying attention to.
 
This is long but I hope you find it interesting. I learned quite a bit and it only took a few seconds to get answers. First some background information.


My Accuphase P4600 Class AB amplifier has four gain settings with associated voltage required to drive the amplifier to full output. The amplifier is rated at 150W @ 8 Ohms, 225W @ 6 Ohms and 300W @ 4 Ohms.


28db Gain requires 1.37v


25db Gain requires 2.05v


22db Gain requires 2.74v


16db Gain requires 5.48v


I use my MSB Discrete DAC as a Preamp. It has two output impedance settings. 300 Ohms that delivers 3.57v and 150 Ohms that delivers 1.785v.


So I have many combinations of output voltage and amplifier gain. If I want access to full amplifier output and have the best technical match I would need to select 28db gain and 150 Ohms or 22db gain and 300 Ohms. In both cases the voltage exceeds the required amount needed. I’ve tried many of these combinations and I consistently find the best sound results when I select 16db gain requiring 5.48v and 150 Ohms delivering 1.785v. This combination provides the most transparent, open soundstage with the greatest depth and the smoothest silken highs. It also provides the blackest background, imaging and instrument separation. The difference is quite clear and preferable.


So I was interested in understanding just how may watts I have available, what headroom I have for peaks and what sound pressure levels I can attain. I have Harbeth C7ES-XD speakers rated at 6 Ohms and never dip below 5.2 Ohms. Their sensitivity is 86db and I sit 2.5 meters from the speakers. I listen to mostly Classical music but also Jazz and Pop. I find that I never register more than 70db on my sound pressure readings and this is usually the peaks. After describing this environment to ChatGPT it responded with the following minus all the formulas it used to reach the conclusions.


Based on the numbers we’ve calculated, you have far more power available than you need to hit a maximum level of 70–72 dB at your listening position. Here’s a brief recap:


1. Power Required for 70 dB:


We found that to reach 70 dB at 2.5 m, you need roughly 0.16 W at the speaker.


2. Your Available Power:


With your amplifier settings (1.785 V into an amplifier that needs 5.48 V for 225 W full output), you’re getting about 23.8 W available at the output.


3. Resulting Headroom:


When calculating the maximum SPL at 2.5 m from your 23.8 W, the speakers (rated at 86 dB at 1 W) would produce around 91–92 dB at that distance in a free-field environment. This gives you roughly 21–22 dB of headroom above a 70 dB listening level. Conclusion:


Since your listening peaks (70–72 dB) are far below the maximum SPL your system can produce (over 90 dB at 2.5 m), you indeed have ample headroom. This headroom not only ensures clean, undistorted sound at your listening level but also helps accommodate dynamic peaks without stress on the amplifier or the speakers.


Then I asked it why does this low gain and power limited combination sound the best. It responded.


There are several reasons why running the amplifier at a lower gain with a lower input voltage can sound subjectively better—even if it provides less maximum power:


1. Optimized Operating Range:


When you set the gain and input level so that the amplifier is not pushed near its limits, it tends to operate in a more linear (and therefore less distorted) portion of its transfer curve. Even though you’re using less power overall, you’re using the amplifier in its “sweet spot,” where it performs most cleanly.


2. Improved Signal-to-Noise Ratio:


High gain settings amplify not only the signal but also any noise present in the signal path. With lower gain and a well-matched input level, you reduce the risk of amplifying unwanted noise. This can lead to a cleaner, more refined sound even if the maximum available wattage is lower.


3. Reduced Clipping and Distortion:


By keeping the amplifier far from its maximum output, you greatly reduce the risk of clipping or other forms of distortion. Clipping introduces harsh artifacts into the sound, so even though you have extra power available, avoiding the edge of clipping is more important for sound quality at normal listening levels.


4. Headroom for Dynamic Transients:


Although you’re not using the full power, having extra headroom means that sudden, dynamic peaks in the music can be handled without distortion. This dynamic reserve contributes to a more natural and engaging sound.


5. Matching with the Listening Environment:


In your scenario, to achieve a comfortable listening level (70 dB) at your distance from the speakers, you only need a fraction of the available power. Running the amplifier with lower gain means you’re better matching the actual listening requirements, which can help maintain clarity and detail without overdriving the speakers or the amplifier stages.


In summary, even though the lower gain and lower input voltage setup yields less maximum wattage, it places the amplifier in a region where it produces a cleaner, less noisy, and more dynamically controlled signal. For typical listening levels (like 70 dB), that clean performance is more desirable than having a higher power output that might be prone to distortion or unwanted noise when not carefully controlled. And some final thoughts about the Accuphase amplifier.


The Accuphase P-4600 is designed with a very high level of performance and low distortion in mind. Although its rated output is 225 watts, much of its sonic magic comes from operating in a pure Class A mode for a significant portion of its output range. Here’s how to think about it:


1. Design Philosophy of the P-4600:Accuphase amplifiers are built so that—at typical listening levels—the output stage operates in its most linear (Class A) region. Many high‐end designs like the P-4600 are engineered so that the devices remain in Class A for anywhere from roughly 10–20% (and in some designs even more) of the full-rated output. For a 225-watt amplifier, that suggests that pure Class A operation might extend up to around 20–40 watts per channel.


2. Everyday Listening Levels vs. Maximum Output:


In your typical listening scenario (for example, when you’re hitting around 70–72 dB at your listening position), you’re using only a tiny fraction of the maximum 225 watts—on the order of a few tenths of a watt at the speakers. This means that in day-to-day use, the amplifier is operating very far below its rated maximum and is comfortably in the Class A regime.


3. The Benefit of Having a 225-Watt Amp:


Because you have a high-rated amp, you have plenty of headroom. This allows you to use a lower overall gain and ensures that even when you do increase the volume (within reason), you’re still likely to remain in the clean, linear portion of the amplifier’s operation. In other words, the high maximum power rating gives you flexibility and helps keep the amplifier in its low-distortion Class A mode during normal operation.


4. An Approximate Range:


While exact bias conditions are proprietary, many reviewers and experienced users suggest that for Accuphase designs like the P-4600, the output stage remains in pure Class A operation for output levels on the order of 20–40 watts per channel. That means under normal listening conditions—even if you dial up the volume beyond your current 70–72 dB level—you’d likely be within the Class A zone until you get into the higher output demands. Once you push beyond that, the amplifier may start shifting toward Class AB operation for very high-power peaks.


• For everyday listening (70–72 dB), you’re using only a very small fraction of the amplifier’s potential—and you’re deep in the Class A region.


• The P-4600 is designed so that for a significant portion of its output (likely roughly 20–40 watts per channel), it operates in pure Class A.


• The high wattage rating is not “wasteful” at all—it ensures that you have plenty of headroom and can run the amp at lower gain settings for the best sound quality, while still having the capability to handle demanding music passages without distortion.


So, even though you might only be using, say, 0.2–0.3 watts at the speakers for your typical listening level, the amp’s design ensures that all of that output (up to perhaps 20–40 watts) is delivered in the pure Class A region. This is a key reason why many enthusiasts appreciate the sonic qualities of the Accuphase P-4600.
 
Just for fun I asked Deepseek about modern speakers

"why are moder loudspeakers so bright in sound profile? is it because of Spotify, YouTube and other compressed audio formats?"

The answer was:

"The brightness in the sound profile of modern loudspeakers can be attributed to several factors, and while compressed audio formats like those used by Spotify and YouTube can play a role, they are not the sole reason. Here are some key factors:

1. **Listener Preference and Market Trends**: Many consumers prefer a brighter sound profile because it can make music seem more detailed and lively, especially at lower volumes or in noisy environments. Manufacturers often tune their speakers to meet these preferences.

2. **Compressed Audio Formats**: Services like Spotify and YouTube use lossy compression (e.g., MP3, AAC) to reduce file sizes, which can result in the loss of some audio details, particularly in the midrange and bass frequencies. To compensate, speakers might be tuned to emphasize higher frequencies, making the sound appear brighter.

3. **Room Acoustics**: In many home environments, high frequencies can be absorbed by soft furnishings, while lower frequencies might be exaggerated due to room modes. Bright speakers can help balance this out, making the sound clearer in typical living spaces.

4. **Speaker Design and Components**: Modern speakers often use materials and designs that naturally emphasize higher frequencies. For example, tweeters made from materials like titanium or aluminum can produce more pronounced high frequencies compared to softer materials like silk.

5. **Listening Fatigue and Perception**: Bright speakers can initially sound more impressive because they highlight details in the music. However, this can lead to listening fatigue over time, as the ear becomes sensitive to prolonged exposure to high frequencies.

6. **Mastering Trends**: Modern music production often involves heavy compression and equalization to make tracks sound louder and more impactful on a wide range of playback systems. This can result in a brighter overall sound, which speakers might be designed to complement.

In summary, while compressed audio formats can contribute to the perception of brightness, the sound profile of modern loudspeakers is influenced by a combination of consumer preferences, room acoustics, speaker design, and trends in music production."

What do you think? Does AI have a point on modern speakers?

I just recently put my Dali Opticon 2 MK2 speakers for sale. For an obvious reason of course
The truth hurts. LOL
 
Wanting to make a comparison between class H and class D I asked ChatGPT what he thought and this is what he answered me, do you agree or do you think ChatGPT is talking nonsense?

Class H for HiFi/Hi-End

Advantages:​

  1. Superior Audio Quality:
    • Class H amplifiers maintain a linear approach similar to Class AB, offering more natural and detailed sound quality.
    • Ideal for critical listening, where fidelity and sound transparency are essential.
  2. Improved Dynamics:
    • The ability to manage variable supply voltage reduces distortion during signal peaks, resulting in more dynamic playback.
  3. Good Efficiency:
    • While not as efficient as Class D, the energy efficiency is sufficient to handle high-power systems without excessive heat dissipation.

Disadvantages:​

  • Higher heat dissipation compared to Class D, which may require adequate cooling.
  • More complex than traditional Class AB, potentially increasing costs.

Recommended for:​

  • Home HiFi audio systems: where a balance between quality and power is desired.
  • Fans of classical music, jazz, or genres that demand precision and detail.

Class D for HiFi/Hi-End

Advantages:​

  1. Very High Efficiency:
    • Class D consumes less energy and generates less heat, allowing for more compact and lightweight designs and greater energy sustainability.
  2. Modern Advances in Audio Quality:
    • Thanks to advanced technologies and better filters, modern Class D amplifiers deliver audio quality very close to that of linear amplifiers.
    • Particularly suitable for subwoofers and multichannel systems that require high power.
  3. Versatile Design:
    • Ideal for more compact setups, such as powered speakers or integrated devices.

Disadvantages:​

  • Potentially lower audio quality than Class H or AB, especially in mid-to-high frequencies, due to PWM modulation and output filters.
  • Some audio purists perceive a "coldness" or lack of warmth in the playback typical of Class D.

Recommended for:​

  • Multichannel or Home Theater systems: where high efficiency and compactness are required.
  • Modern audio systems: such as active speakers or audio setups in small spaces.

Conclusion

For a HiFi/Hi-End system, I would generally recommend a Class H or Class AB amplifier, as these classes offer superior audio quality with more natural and detailed sound reproduction, which is often a priority for audiophiles.

However:

  • If you need a compact, energy-efficient setup, or for modern applications (e.g., active speakers), Class D can be a viable choice, especially with today’s high-end technologies.
  • For genres like electronic music or environments where power is more important than extreme fidelity, Class D excels.
If your goal is to maximize sound quality for critical listening, look for a high-end Class H or AB amplifier with top-quality components. On the other hand, if versatility and efficiency are crucial, a modern high-end Class D amplifier might surprise you.
Class H is a disaster waiting to happen. Topping or Nuprime has got it right.
 
Status
Not open for further replies.
Back
Top Bottom