Chat GPT: WOW.

[NoxMorbis]

I got this from ChatGPT:

ME: Does the Texas instruments 3255 amplifier chip have built in spike protection for clipping?

CHATGPT: Yes, the Texas Instruments TPA3255 amplifier chip does have built-in spike protection to prevent clipping and potential damage to the amplifier or speakers.
The TPA3255 chip includes a range of protection features, including over-current protection, over-temperature protection, and DC speaker protection. In addition, the chip has a built-in limiter to prevent clipping by dynamically adjusting the gain of the amplifier in response to the input signal level. The limiter works by reducing the gain of the amplifier when the input signal level exceeds a certain threshold, preventing the signal from reaching the maximum output level of the amplifier. The TPA3255 chip also includes a range of diagnostic and monitoring features, including DC offset detection, fault reporting, and thermal monitoring, which can help to improve the reliability and safety of the amplifier. Overall, the TPA3255 chip is designed to provide high-quality audio performance while ensuring the safety and protection of the amplifier and speakers.

LOL. Wow. Still doesn't tell us how it is implemented and when I asked about the 08 Pro, it said it didn't know because the specifications information is not available.

 

[voodooless]

But is it true? The datasheet doesn’t say anything about a dynamic limiter for clipping..

 

[Jim Shaw]

It is wrong to expect AI to be factually correct all the time. Its database is the internet, and we all know how un-flawless that can be.
So far, AI is correct about as often as a gypsy fortune teller. It's just cheaper.

 

[abdo123]

It is wrong to expect AI to be factually correct all the time. Its database is the internet, and we all know how un-flawless that can be.
So far, AI is correct about as often as a gypsy fortune teller. It's just cheaper.

Or just a regular person to be honest. People are rarely correct about everything.

 

[Jim Shaw]

You might enjoy this ChatGPT exchange:

Q: How many angels can dance on the head of a pin?

The question of how many angels can dance on the head of a pin is a theological and philosophical question that has been debated for centuries. The question was first posed by medieval Christian philosophers, but it is not a question that can be answered with a specific number, as it is not based on any empirical or scientific evidence.
Some scholars have interpreted the question as a metaphor for pointless intellectual debates that have no real-world significance. Others have argued that the question is an example of the limitations of human understanding and the nature of the divine. Ultimately, the answer to the question depends on one's perspective and beliefs.

 

[NoxMorbis]

But is it true? The datasheet doesn’t say anything about a dynamic limiter for clipping..

I forgot to ask it where it got the information, specifically, but it will give you that information too.

 

[Jim Shaw]

You might enjoy this ChatGPT exchange:

Q: How many angels can dance on the head of a pin?

The question of how many angels can dance on the head of a pin is a theological and philosophical question that has been debated for centuries. The question was first posed by medieval Christian philosophers, but it is not a question that can be answered with a specific number, as it is not based on any empirical or scientific evidence.
Some scholars have interpreted the question as a metaphor for pointless intellectual debates that have no real-world significance. Others have argued that the question is an example of the limitations of human understanding and the nature of the divine. Ultimately, the answer to the question depends on one's perspective and beliefs.

Followup question:

How many minutes does Steve G. listen to a speaker before reviewing it?
-or-
What brand of cereal box did Danny cut his engineering degree from?

 

[NoxMorbis]

I put it through it's paces using a conversation about space, specifically about time and space, that is, "duration," and its necessary condition of human knowledge. At first it gave interesting but unimpressive answers, but as I narrowed down the questions, it did produce correct answers. It's logic is impeccable, but in order to get to that point, you need to know exactly what you want. For instance, I asked it how it could even talk about a durationaless object, which produces a contradiction. It admitted it was a contradiction. However, we needed to have a discussion about what an object is, which is the everyday scientific definition.

I started by asking it if it could understand the space a car occupied in a parking space as not existing. It said yes that it could understand an empty parking space. lol. After making it more clear, it admitted that human understanding necessitates concepts of space, so no, it wasn't possible.

Anyway, a wonderful research tool being born.

 

[fpitas]

After all the marketing noise about Chat GPT, I still think it's main use will be writing stuff for lazy college students.

 

[NoxMorbis]

Followup question:

How many minutes does Steve G. listen to a speaker before reviewing it?
-or-
What brand of cereal box did Danny cut his engineering degree from?

It cannot answer those question, and it will tell you exactly why. I actually told it that it sounded more like a librarian with information immediately accessable, but did not feel like true AI in that it wasn't thinking on its own. It replied that I was correct, that it is a "language AI" in the sense it can learn to talk in human terms, but it cannot do its own thinking. Then it said that other AIs can, such as scientific AIs, but we normal people don't have access to them.

 

[NoxMorbis]

After all the marketing noise about Chat GPT, I still think it's main use will be writing stuff for lazy college students.

More like researching how to do stuff, like we already do, but a LOT faster. Cheater are going to cheart, and they completely miss the tools true function in doing so. When colege students cheat, they jsut cheat themselves becsaue they don;t get the educational benefit. Like I told someone lese about Chat GPT: People can pretend all tehy want, but when you meet them face to face, they are still stupid. lol

 

[fpitas]

More like researching how to do stuff, like we already do, but a LOT faster. Cheater are going to cheart, and they completely miss the tools true function in doing so. When colege students cheat, they jsut cheat themselves becsaue they don;t get the educational benefit. Like I told someone lese about Chat GPT: People can pretend all tehy want, but when you meet them face to face, they are still stupid. lol

That's all true. It won't stop any of them from cheating, though.

 

[NoxMorbis]

That's all true. It won't stop any of them from cheating, though.

Before chat GPT, you could go into the back of English oriented literature magazines and find ads where people would write your research paper for a C, B, or A grade with each level increasing in price. lol It use to piss me off. My English professor said, "That's what we get when we have unemployed English majors." lol

 

[fpitas]

Before chat GPT, you could go into the back of English oriented literature magazines and find ads where people would write your research paper for a C, B, or A grade with each level increasing in price. lol It use to piss me off. My English professor said, "That's what we get when we have unemployed English majors." lol

Lots of paid "Essay writing" services online, too. From what I've seen, Chat GPT has much better grammar, although factually it may be no better.

 

[voodooless]

My English professor said, "That's what we get when we have unemployed English majors." lol

Clearly it’s an English professor, not a logic professor. If they’re making money making others homework, they are clearly employed

 

[NoxMorbis]

It is wrong to expect AI to be factually correct all the time. Its database is the internet, and we all know how un-flawless that can be.
So far, AI is correct about as often as a gypsy fortune teller. It's just cheaper.

It's simply an interface for a repository of information, and if you give it unclear instructions, it will give you erroneous output.

 

[NoxMorbis]

Clearly it’s an English professor, not a logic professor. If they’re making money making others homework, they are clearly employed

LOL, yeah, they are!

 

[voodooless]

It's simply an interface for a repository of information, and if you give it unclear instructions, it will give you erroneous output.

No, it much worse. It will just make stuff up also when totally not appropriate.

I asked it to list a few software libraries to do a specific function, and the first one it came up with was totally fictional.

Once confronted it made some empty apologies

 

[fpitas]

No, it much worse. It will just make stuff up also when totally not appropriate.

I asked it to list a few software libraries to do a specific function, and the first one it came up with was totally fictional.

Once confronted it made some empty apologies

It sounds ready for politics.

 

[baonguyen]

I put it through it's paces using a conversation about space, specifically about time and space, that is, "duration," and its necessary condition of human knowledge. At first it gave interesting but unimpressive answers, but as I narrowed down the questions, it did produce correct answers. It's logic is impeccable, but in order to get to that point, you need to know exactly what you want. For instance, I asked it how it could even talk about a durationaless object, which produces a contradiction. It admitted it was a contradiction. However, we needed to have a discussion about what an object is, which is the everyday scientific definition.

I started by asking it if it could understand the space a car occupied in a parking space as not existing. It said yes that it could understand an empty parking space. lol. After making it more clear, it admitted that human understanding necessitates concepts of space, so no, it wasn't possible.

Anyway, a wonderful research tool being born.

Chat GPT is better for brainstorming content ideas than asking data-driven questions.