ChatGPT - I asked some questions - You should too!

[DarkMode]

I had the idea of asking ChatGPT all about Electricity.

I've been find it very useful for explaining how it works, I highly Recommend beginners to ask your Questions to ChatGPT, it never gets offended and you can Asked it again and again to rephrase it for you.

I have asked it to explain Voltage and Current, Electron Drift and Maxwell's Equations, does Electron Spin create electricity, Poynting Vectors... all those gritty details that you will be hard to find elsewhere with 1 Exception The Science Asylum
https://www.youtube.com/playlist?list=PLOVL_fPox2K9MtRv68T_cmWwQUbg9YR4F

It's only been about 6 months since I discovered Veritasium's Video and his Follow up. In following the trail, I then found Rick Hartley (PCB designer), followed by Eric Bogatin, and Others:
Most useful of these the Altium Designer videos (PCB software company) has been posting their keynote speakers and I've learnt so much.

Rick Hartley at Altium
 

I just want to say, that Steady State DC works great with Lumped Models, until ... we add variation (Transient) into our circuits, as in anything that Switches, a 555 timer, a Microcontroller, a Mosfet.

The Reality is that we will not get to talk to EE's that understand Maxwell's equations or Poynting vectors.

I would like to think that this information can get some hobbyists mind out of the Water Model and into the Electromagnetic Field Model.

Some might argue that I'm creating division or confusion, I would say I'm bridging the baby steps we have been taught towards better understanding of the Universe (The Electromagnetic Universe)

What's the difference between Light (you see with your eyes) and energy in a circuit?

Do you have Questions? Ask GPT




Answer: frequency
Think about this then, how do we create Radio Waves from electronic parts to be transmitted into 'thin air'

[Ed.Kloonk]

Why am I so soft in the middle when the rest of my life is so hard?

[Ranayna]

Can someone who asks ChatGPT questions about a subject that they do not know, ever really trust any answer that ChatGPT gives?

ChatGPT knows language, and it knows language almost scarily well, but not facts. It is also well known that ChatGPT invents "facts" and also can change "facts" when pressured.
But since it knows language so well, it can be very convincing with it's "facts".

[Ed.Kloonk]

Can someone who asks ChatGPT questions about a subject that they do not know, ever really trust any answer that ChatGPT gives?

ChatGPT knows language, and it knows language almost scarily well, but not facts. It is also well known that ChatGPT invents "facts" and also can change "facts" when pressured.
But since it knows language so well, it can be very convincing with it's "facts".

Ask a four year old, why is the sky blue?

[Bud]

@OP did you ask ChatGPT to write your post ?

[LinuxHata]

I asked a simplest way to convert DC to AC and it suggested to use bridge rectifier.
Not joking, no typo, I have screenshots somewhere, but you can ask by yourself.

[radiolistener]

ChatGPT is very stupid when it comes to the exact sciences, in particular electrodynamics or math. It knows a lot of knowledge pieces from different science sources, but ChatGPT don't know how to use this knowledge to draw any useful conclusions.

The worse thing is that ChatGPT always write false math equations and ascribes authorship to non-existent scientific papers or gives links to scientific papers where there is nothing like what he cites.

You can use ChatGPT as a more cunning search engine than google, but you can't believe to things which he says, you're always needs to search original primary source and check any fact that ChatGPT claims.

Unfortunately about 95% of information taken from ChatGPT and related to exact science (such as physics, math, etc) is false and misleading. So I would not suggest to learn something from ChatGPT. 

[Terry Bites]

Ask it how many jobs it will destroy and how many jobs AI will create.
Its great at waffle, where did it learn that?

[DarkMode]

Ask it how many jobs it will destroy and how many jobs AI will create.
Its great at waffle, where did it learn that?

What jobs did I destroy by asking ChatGPT questions that you wouldn't give the time of day for?

[DarkMode]

I asked a simplest way to convert DC to AC and it suggested to use bridge rectifier.
Not joking, no typo, I have screenshots somewhere, but you can ask by yourself.

OK, but I'm not here to defend ChatGPT and its responses, that's ridiculous.   
Also why would you use it for something obvious? it's a conversation, did you correct it? Ask it that the response was backwards?

I asked it "what do I use to change DC to AC?"
This is the Answer:

To convert DC (direct current) to AC (alternating current), you can use a device called an inverter. An inverter is an electronic device that converts the steady flow of DC power into an alternating current that periodically changes direction.

There are different types of inverters available, but the most common type is a solid-state inverter. Solid-state inverters use semiconductor devices, such as transistors or insulated gate bipolar transistors (IGBTs), to convert DC to AC. They operate by rapidly switching the DC input voltage on and off, creating a pulsating waveform that can be further processed to generate a sinusoidal AC output.

Here are the general steps involved in the DC to AC conversion process using an inverter:

Rectification: If the input DC voltage is not already steady, it may need to be rectified using a diode bridge or other rectification circuit to convert it to a smooth DC voltage.

Inversion: The DC voltage is fed into the inverter circuit, which consists of semiconductor switches. These switches are controlled to rapidly switch the DC voltage on and off, typically at high frequencies.

Pulse Width Modulation (PWM): To generate a sinusoidal AC output, the on and off switching of the DC voltage is controlled using a technique called pulse width modulation. By varying the width of the pulses, the desired AC waveform can be approximated.

Output Filtering: The output of the inverter, which initially consists of a series of pulses, is then passed through filters, such as LC (inductor-capacitor) filters, to smooth out the waveform and remove any unwanted harmonics.

The resulting output of the inverter is an AC waveform that can be used to power AC devices or be connected to an AC power grid.

It's worth noting that the specific design and operation of inverters can vary depending on the application and power requirements. Different types of inverters, such as square wave, modified sine wave, or pure sine wave inverters, may be used depending on the desired quality and compatibility of the AC output waveform.

Overall, an inverter is the primary device used to convert DC to AC power in various applications, such as solar power systems, uninterruptible power supplies (UPS), and portable electronic devices.

[DarkMode]

Some might argue that I'm creating division or confusion, I would say I'm bridging the baby steps we have been taught towards better understanding of the Universe (The Electromagnetic Universe)

I thought you were just being too lazy to read a university textbook. Actually the first two videos were covered in highschool decades ago for me.

So, your smart and completed 12 years of schooling and more, well done human 

Can I ask your IQ?

[DarkMode]

Can someone who asks ChatGPT questions about a subject that they do not know, ever really trust any answer that ChatGPT gives?

ChatGPT knows language, and it knows language almost scarily well, but not facts. It is also well known that ChatGPT invents "facts" and also can change "facts" when pressured.
But since it knows language so well, it can be very convincing with it's "facts".

Ask a four year old, why is the sky blue?

I asked ChatGPT why the sky is blue:

The sky appears blue due to a phenomenon known as Rayleigh scattering. Rayleigh scattering is the scattering of light by particles or molecules that are much smaller than the wavelength of the light.

In Earth's atmosphere, the primary molecules responsible for Rayleigh scattering are nitrogen and oxygen. These molecules are much smaller than the wavelengths of visible light, particularly in the shorter blue and violet wavelengths. When sunlight, which contains a spectrum of colors, enters Earth's atmosphere, it encounters these tiny molecules.

The blue and violet wavelengths of light have shorter wavelengths and higher frequencies compared to other colors in the spectrum. Due to the size of the nitrogen and oxygen molecules, they scatter these shorter wavelengths more effectively in all directions. This scattering is inversely proportional to the fourth power of the wavelength, as described by Rayleigh's scattering law.

As a result of the scattering, the blue and violet light is scattered more in all directions, including towards our eyes. This scattered blue light from different parts of the sky combines and reaches our eyes, making the sky appear blue. In contrast, the longer-wavelength colors like red, orange, and yellow are scattered less and tend to pass through the atmosphere with less scattering, giving rise to the colors we see during sunrise or sunset when the sunlight passes through a greater thickness of the atmosphere.

It's important to note that the scattering of light by other particles and aerosols in the atmosphere can also contribute to variations in the color of the sky under different atmospheric conditions. However, the dominant reason for the sky appearing blue is the Rayleigh scattering of sunlight by nitrogen and oxygen molecules in the Earth's atmosphere.

Oh Yes, 4 year olds will answer just like this 

[DarkMode]

Why am I so soft in the middle when the rest of my life is so hard?

Why reply with Non-sense 

[DarkMode]

@OP did you ask ChatGPT to write your post ?

I didn't ask ChatGPT to write this post, it took Effort on my part. Was there some information you wanted to exchange?

[DarkMode]

I asked ChatGPT who Heaviside was. Who is Heaviside? Why was Heaviside important?

I would of asked the Forum and you would of given the Wikipedia page or just ignored it.

If I looked at all the responses to my post, 0 were positive, some were sceptical about ChatGPT and others were questioning if I'm human 

Why would I bother with YOU?

This is the reason I wrote this post, as I said, NO EE or Advanced Electrician is going to take your question seriously, then it's good to learn it from something other than. One tool is ChatGPT.

 

Some might argue that I'm creating division or confusion, I would say I'm bridging the baby steps we have been taught towards better understanding of the Universe (The Electromagnetic Universe)

I thought you were just being too lazy to read a university textbook. Actually the first two videos were covered in highschool decades ago for me.

Yeah, I'm dumb. I never completed high school and Electrical Engineering wasn't in my school, even if it was, I quit at Year 10. Thanks for that  Then again I'm the smartest person I know in my household, I can ask my neighbour about how Electrical Power flows though to their house, and will be looking at me like I'm crazy  I'll tell him to go read a University or High School text book or that they were too Lazy to even look it up. Worked for you right?  I've been called dumb plenty of times before, sticks and stones 

[DarkMode]

ChatGPT is very stupid when it comes to the exact sciences, in particular electrodynamics or math. It knows a lot of knowledge pieces from different science sources, but ChatGPT don't know how to use this knowledge to draw any useful conclusions.

The worse thing is that ChatGPT always write false math equations and ascribes authorship to non-existent scientific papers or gives links to scientific papers where there is nothing like what he cites.

You can use ChatGPT as a more cunning search engine than google, but you can't believe to things which he says, you're always needs to search original primary source and check any fact that ChatGPT claims.

Unfortunately about 95% of information taken from ChatGPT and related to exact science (such as physics, math, etc) is false and misleading. So I would not suggest to learn something from ChatGPT. 

Can someone who asks ChatGPT questions about a subject that they do not know, ever really trust any answer that ChatGPT gives?

ChatGPT knows language, and it knows language almost scarily well, but not facts. It is also well known that ChatGPT invents "facts" and also can change "facts" when pressured.
But since it knows language so well, it can be very convincing with it's "facts".

This Screams Trust me Bro   

[DarkMode]

I asked ChatGPT:
differential pairs in 2 wires vs on a pcb is there a difference?

Differential pairs refer to a method of transmitting electrical signals using two closely spaced wires or traces. This technique is commonly used to mitigate the effects of electromagnetic interference (EMI) and noise in high-speed data transmission.

When discussing differential pairs, there can be a difference between using two wires in a general wiring scenario compared to implementing them on a printed circuit board (PCB).

In a general wiring scenario, such as in an analog or audio application, differential pairs can be implemented using two separate wires that are twisted together. The twisting helps to reduce common-mode noise and interference by ensuring that any external signals affect both wires similarly, allowing the receiving end to extract the desired differential signal.

On a PCB, differential pairs are typically implemented as closely spaced traces that run parallel to each other, often with a consistent impedance between the two traces. This design approach is commonly used for high-speed digital data transmission, such as in Ethernet, USB, or HDMI interfaces.

Implementing differential pairs on a PCB allows for controlled impedance and improved signal integrity. The closely spaced traces help to minimize electromagnetic coupling with external noise sources, such as other traces or nearby components. Additionally, maintaining a consistent impedance along the length of the traces helps to reduce signal reflections and maintain signal integrity.

On a PCB, additional considerations are taken into account to ensure the proper implementation of differential pairs. These considerations include impedance control, trace length matching, proper termination techniques, and adherence to high-speed design guidelines. PCB design tools and techniques, such as differential pair routing rules and impedance calculators, are often used to optimize the performance of differential pairs on a PCB.

In summary, while the basic concept of differential pairs remains the same, there can be differences in implementation between using two wires in a general wiring scenario and implementing them on a PCB. The PCB implementation involves specific considerations to achieve controlled impedance, minimize noise, and ensure signal integrity in high-speed digital data transmission.

Result: Facts      Humans  Too busy insulting each other 

[DarkMode]

Corrected for the Playlist. Individual video from The Science Asylum was a mistake

https://www.youtube.com/playlist?list=PLOVL_fPox2K9MtRv68T_cmWwQUbg9YR4F

[liaifat85]

For guidelines about PCB designing software, I did not find ChatGPT much dependable.

[radiolistener]

This Screams Trust me Bro   

No, this is just my finding after many attempts to get some answer from chat-gpt. Usually chat-gpt going into loop like this:

>> Q: give me that estimation for params A and B
>> A: the answer is C
>> Q: this is incorrect answer you have mistake on step X and used incorrect formula and on step Y where you get incorrect calculations, fix it
>> A: sorry for that, here is fixed answer D
>> Q: this is incorrect answer you're needs to use formula (J) on step X, fix it
>> A: the answer is E
>> Q: this is incorrect answer, you have mistake on step Z, fix it
>> A: sorry for that, here is fixed answer C
>> Q: this is incorrect answer you have mistake on step X and used incorrect formula and on step Y
....

Just a simple example how chat-gpt doing "calculations":

Q: Here is equation x^x=1000. Solve it.

A: To solve the equation x^x = 1000, we can use numerical methods or an approximation approach. Since there is no simple algebraic method to solve this equation, we will use an iterative method to find an approximate solution.

Let's start by guessing a value for x and then refine it through iterations until we get a close approximation.

Let's try x = 4:
4^4 = 256 (less than 1000)

Let's try x = 5:
5^5 = 3125 (greater than 1000)

Since the solution lies between 4 and 5, we can perform further iterations to narrow down the range.

Let's try x = 4.5:
4.5^4.5 ≈ 620.92 (less than 1000)

Let's try x = 4.6:
4.6^4.6 ≈ 827.93 (less than 1000)

Let's try x = 4.7:
4.7^4.7 ≈ 1099.5 (greater than 1000)

From these iterations, we can see that the solution lies between 4.6 and 4.7.

Continuing with smaller increments, we can find a more accurate solution:

Let's try x = 4.65:
4.65^4.65 ≈ 982.97 (less than 1000)

Let's try x = 4.66:
4.66^4.66 ≈ 1002.82 (greater than 1000)

From this, we can conclude that the approximate solution to the equation x^x = 1000 is x ≈ 4.65.

As you can see it gives you incorrect calculations and as result incorrect answer.

Just FYI:
4.5^4.5 ≈ 620.92 is incorrect, the correct answer is 4.5^4.5 ≈ 869.87
4.6^4.6 ≈ 827.93 is incorrect, the correct answer is 4.6^4.6 ≈ 1118.62
4.7^4.7 ≈ 1099.5 is incorrect, the correct answer is 4.7^4.7 ≈ 1441.65
4.65^4.65 ≈ 982.97 is incorrect, the correct answer is 4.65^4.65 ≈ 1269.57
4.66^4.66 ≈ 1002.82 is incorrect, the correct answer is 4.66^4.66 ≈ 1302.20
The total answer x ≈ 4.65 is incorrect, the correct answer is x ≈ 4.556.

As you can see, chat-gpt just provide you with false calculations and you believe that it's truth, but in reality it is false. The same thing happens with almost any calculations provided by chat-gpt, it almost always has mistakes and misleading you. The same thing happens with formulas, it can provide you with some invalid formula which looks very similar to the truth, but in reality it is false. If you ask chat-gpt where he got that formula it provide you some science paper name. But in reality there is no such science paper, or if it exists, there is no such formula at all. If you notice that there is no such source, or it doesn't have such formula it provide you another science source name, also false. I tried to get the right source, but chat-gpt provided me dozens of non-existent scientific articles or existing but without any mention about formula which he used.

After dozen attempts I realized, that if chat-gpt provided you with false information, you will be unable to get correct answer from chat-gpt, even if you provide detail explanation of every chat-gpt mistake...

You cannot believe chat-gpt, because most of things that it provides you is a false information, but it's very nicely framed, so you won't notice it right away.

The main issue of chat-gpt, is that it provides false and misleading information, but it doing it in that way so it looks like truth and if you don't check every detail in chat-gpt answer, you even didn't notice that you're got false information. That's a problem.

[DarkMode]

This Screams Trust me Bro   

No, this is just my finding after many attempts to get some answer from chat-gpt. Usually chat-gpt going into loop like this:

>> Q: give me that estimation for params A and B
>> A: the answer is C
>> Q: this is incorrect answer you have mistake on step X and used incorrect formula and on step Y where you get incorrect calculations, fix it
>> A: sorry for that, here is fixed answer D
>> Q: this is incorrect answer you're needs to use formula (J) on step X, fix it
>> A: the answer is E
>> Q: this is incorrect answer, you have mistake on step Z, fix it
>> A: sorry for that, here is fixed answer C
>> Q: this is incorrect answer you have mistake on step X and used incorrect formula and on step Y
....

Just a simple example how chat-gpt doing "calculations":

Q: Here is equation x^x=1000. Solve it.

A: To solve the equation x^x = 1000, we can use numerical methods or an approximation approach. Since there is no simple algebraic method to solve this equation, we will use an iterative method to find an approximate solution.

Let's start by guessing a value for x and then refine it through iterations until we get a close approximation.

Let's try x = 4:
4^4 = 256 (less than 1000)

Let's try x = 5:
5^5 = 3125 (greater than 1000)

Since the solution lies between 4 and 5, we can perform further iterations to narrow down the range.

Let's try x = 4.5:
4.5^4.5 ≈ 620.92 (less than 1000)

Let's try x = 4.6:
4.6^4.6 ≈ 827.93 (less than 1000)

Let's try x = 4.7:
4.7^4.7 ≈ 1099.5 (greater than 1000)

From these iterations, we can see that the solution lies between 4.6 and 4.7.

Continuing with smaller increments, we can find a more accurate solution:

Let's try x = 4.65:
4.65^4.65 ≈ 982.97 (less than 1000)

Let's try x = 4.66:
4.66^4.66 ≈ 1002.82 (greater than 1000)

From this, we can conclude that the approximate solution to the equation x^x = 1000 is x ≈ 4.65.

As you can see it gives you incorrect calculations and as result incorrect answer.

Just FYI:
4.5^4.5 ≈ 620.92 is incorrect, the correct answer is 4.5^4.5 ≈ 869.87
4.6^4.6 ≈ 827.93 is incorrect, the correct answer is 4.6^4.6 ≈ 1118.62
4.7^4.7 ≈ 1099.5 is incorrect, the correct answer is 4.7^4.7 ≈ 1441.65
4.65^4.65 ≈ 982.97 is incorrect, the correct answer is 4.65^4.65 ≈ 1269.57
4.66^4.66 ≈ 1002.82 is incorrect, the correct answer is 4.66^4.66 ≈ 1302.20
The total answer x ≈ 4.65 is incorrect, the correct answer is x ≈ 4.556.

As you can see, chat-gpt just provide you with false calculations and you believe that it's truth, but in reality it is false. The same thing happens with almost any calculations provided by chat-gpt, it almost always has mistakes and misleading you. The same thing happens with formulas, it can provide you with some invalid formula which looks very similar to the truth, but in reality it is false. If you ask chat-gpt where he got that formula it provide you some science paper name. But in reality there is no such science paper, or if it exists, there is no such formula at all.

You cannot believe chat-gpt, because most of things that it provides you is a false information, but it's very nicely framed, so you won't notice it right away.

Thanks for that, I know you took time and effort into making this reply

I think you are using ChatGPT incorrectly, here you expect it to know to calculate, this is not the function of ChatGPT.
If I opened an Encyclopaedia and searched for Algebra expressions, it will give me the information on what Algebra is, not necessarily how to solve an individual problem.
You can Ask it for suggestions, but's it's not the personal assistant we hoped for, it's a Encyclopaedia-Ai addition.

It also depends on the USER and their expectations; you asked a Language Model to Solve math problems.
Pst - That's what Google is For 
Google solved the problem, but it's not going to explain into words abstract language.

https://www.google.com.au/search?q=4.5+to+the+power+of+4.5&source=hp&ei=Mj2pZPnEINav2roPhMiU6Ak&iflsig=AD69kcEAAAAAZKlLQmqprbP-ChlvSwup6w8H-Hgntc8G&ved=0ahUKEwj5pbGQ9v7_AhXWl1YBHQQkBZ0Q4dUDCAs&uact=5&oq=4.5+to+the+power+of+4.5&gs_lp=Egdnd3Mtd2l6Ihc0LjUgdG8gdGhlIHBvd2VyIG9mIDQuNTIFECEYoAEyBRAhGKABMgUQIRigATIFECEYoAFI850BUMQ7WIOaAXAIeACQAQKYAe4CoAGxM6oBCDEuMi4yMy4zuAEDyAEA-AEBqAIKwgIQEAAYAxiPARjqAhiMAxjlAsICEBAuGAMYjwEY6gIYjAMY5QLCAgsQABiABBixAxiDAcICCxAAGIoFGLEDGIMBwgIIEAAYgAQYsQPCAgUQABiABMICCBAAGIoFGLEDwgIIEAAYgAQYyQPCAgYQABgWGB7CAggQABgWGB4YD8ICCBAAGIoFGIYDwgIIECEYFhgeGB3CAgoQIRgWGB4YDxgdwgIEECEYFQ&sclient=gws-wiz

[baldurn]

ChatGPT is a useful tool. Yes you need to know it's limitations and faults, but that does not make it useless. Someone said above that it is wrong 95% of the time. Actually it is correct between 70% and 99% depending on the domain. This metric is something the creators are measuring of course.

Another points out how it is bad at math. Yes but it gets the method correct. There already exists tools that allows ChatGPT to use a calculator, so it actually calculates correctly. As humans, we wouldn't get these calculations correct either without a calculator.

Learning how to use ChatGPT is becoming an important skill.

[radiolistener]

I think you are using ChatGPT incorrectly, here you expect it to know to calculate, this is not the function of ChatGPT.
If I opened an Encyclopaedia and searched for Algebra expressions, it will give me the information on what Algebra is, not necessarily how to solve an individual problem.

First I found that issue of chat-gpt not related to math. I forgot the original topic, as I remember it was something related to physics, electrodynamics general relativity and philosophy. But it's hard to catch it on general talk, because chat-gpt trying to avoid direct answers. Later I found that it's more easy to catch chat-gpt on these issues with math and calculations, because math doesn't allows vague voluminous responses which can be interpreted in different way, so there is less space for manipulation and more easy to catch chat-gpt on false answer, because answer can be easily checked

That's is interesting note, because it's more easy to learn neural network form exact science like math, because there are present engines which allows to work with formulas and calculations and it can be easily checked, so it should be more easy to learn things like math, but for some reason chat-gpt is very bad with it.

So, I think the main goal of chat-gpt is to manipulate with existing set of information in such way to mislead people and make him believe in some random information, due to the fact that it looks like the truth.

I think chat-gpt (at least at the current level of development) is the best choice for propaganda and manipulation of public opinion. Chat-gpt can easily deceive gullible people, but for RnD (research and development) tasks it is almost useless.

I think the most optimal solution is to consider chat-gpt as a cunning liar who has a lot of information available and his goal is to mislead you and take control on public opinion. Yes, you can get some new information from chat-gpt, but you cannot believe to what he says. And you're needs to check all information obtained from chat-gpt with independent sources.

[DarkMode]

I forgot the original topic, as I remember it was something related to physics, electrodynamics general relativity and philosophy.

  That is correct, sadly my intention was to bring non-technical electronic hobbyists towards the Electrodynamic models
I used the Buzz word and that buzz word took a life on it's own 

End of Line

[SiliconWizard]

Isn't that what all buzz words do?