Is asked ChatGPT: What is Internet Component Suite for Delphi?

[FPiette 384]

[Qasim Shahzad 0]

It is strange how much ChatGPT "Knows" about Delphi and Pascal.

Q. How to use ICS to fetch a webpage
=== === === === === === === === ===
Ans:

To use ICS (Internet Component Suite) to fetch a webpage in Delphi, you can follow these steps:

Make sure that you have ICS installed on your system. If you are using the Embarcadero RAD Studio platform, ICS should already be included.

In your Delphi project, add a reference to the ICS library by going to Project > Add to Project > Import a Type Library.

In the Delphi unit where you want to fetch the webpage, add the following line at the top of the file to import the ICS components:

uses Ics.HttpProt;

Create an instance of the THttpCli component and set its URL property to the address of the webpage you want to fetch. For example:
Copy code
HttpCli.URL := 'https://www.example.com';
Set the HttpCli.RcvdStream property to a TMemoryStream object, which will be used to store the data from the webpage.

Call the HttpCli.GetAsync method to initiate the request to fetch the webpage. This method is asynchronous, which means that it will return immediately and the webpage data will be received in the background.

To receive the data from the webpage, you will need to handle the HttpCli.DocData event. This event is triggered when data is received from the webpage. In the event handler, you can use the HttpCli.RcvdStream property to access the data that was received.

When the request is complete, the HttpCli.DocBegin and HttpCli.DocEnd events will be triggered. You can use these events to clean up any resources that you have allocated and to notify the user that the request has completed.

Here is an example of how you might use these steps to fetch a webpage and display its contents in a TMemo component:Copy code

procedure TForm1.Button1Click(Sender: TObject);
var
  HttpCli: THttpCli;
begin
  HttpCli := THttpCli.Create(nil);
  try
    HttpCli.URL := 'https://www.example.com';
    HttpCli.RcvdStream := TMemoryStream.Create;
    HttpCli.OnDocData := HttpCliDocData;
    HttpCli.GetAsync;
  finally
    HttpCli.Free;
  end;
end;

procedure TForm1.HttpCliDocData(Sender: TObject; Buffer: Pointer;
  Len: Integer);
begin
  Memo1.Lines.LoadFromStream(THttpCli(Sender).RcvdStream);
end;

This is just a basic example, and there are many other features and options available in ICS for more advanced scenarios. You can refer to the ICS documentation for more information.

[mvanrijnen 123]

I got the following answer on the same question:
 

"

ICS (Internet Communications Suite) is a suite of applications that includes several programs for communicating over the internet, such as email, instant messaging, and web browsing. To use ICS to fetch a webpage, you will need to use a web browser program that is part of the ICS suite, such as Netscape Navigator or Mozilla Firefox.

Here is a general outline of the steps you can follow to use ICS to fetch a webpage:

1. Open your web browser program by double-clicking on its icon or selecting it from the list of programs on your computer.

2. In the address bar at the top of the browser window, type the URL (Uniform Resource Locator) of the webpage you want to fetch, and press Enter. The URL is the web address of the webpage, and it typically begins with "http://" or "https://".

3. Wait for the webpage to load. This may take a few seconds or longer, depending on the size of the webpage and the speed of your internet connection.

4. Once the webpage has finished loading, you can scroll through it and interact with any links or buttons on the page.

I hope this helps! Let me know if you have any other questions.

"

[dummzeuch 1506]

On the other hand it told me that GExperts is a library and that it provides the functionality to extract a function. Both are obviously wrong. It also inserts a random name picked from the contributor's list when asked for the maintainer or even the original developer (which was Gerald Nunn in the 1990s as far as I remember, before Erik Berry took over).

It also told me about several functions in the jcl for importing a dll that don't actually exist.

 

Or, for non programming questions: It told me that Wilhelmshaven has a sandy beach with dunes near the Jade Stadium. (No, it hasn't.)

 

The problem with ChatGPT is that its answers are well formulated and appear so plausible, you don't question them.

Edited January 2, 2023 by dummzeuch

[Qasim Shahzad 0]

@dummzeuch

Well, there are many wrong answers, but it will surely improve.

 

The first time I used a pseudo-AI bot ELIZA, it was mind-blowing to my younger self at that time. Of course, Knight rider and many other sci-fi movies were also fascinating. 

 

Now we reached a point where things are going in that direction. Still, we might be a decade or two away from a full-blown system, but things are racing now.

[FPiette 384]

20 minutes ago, Qasim Shahzad said:

Well, there are many wrong answers, but it will surely improve.

You are right. If an answer is wrong, then you may correct it! Use the thumb down on the right of the given answer and explain it is wrong. The system learn from his error.

[dummzeuch 1506]

10 minutes ago, FPiette said:

You are right. If an answer is wrong, then you may correct it! Use the thumb down on the right of the given answer and explain it is wrong. The system learn from his error.

No, its knowledge base is static. It only remembers its answers within a given session. If you start a new one, it will repeat the same mistakes.

It also is not really good at learning within a session. I tried to correct it regarding the procedure extraction functionality and it kept repeating that it is a feature of GExperts.

[FPiette 384]

17 minutes ago, dummzeuch said:

No, its knowledge base is static.

That's not what I read. There are reviewer which will allow or not to enhance the engine. Don't expect your criticism to have an immediate impact. It probably depends on de quality of it and the frequency of the related subject in the questions.

[Rollo62 538]

1 hour ago, dummzeuch said:

Or, for non programming questions: It told me that Wilhelmshaven has a sandy beach with dunes near the Jade Stadium. (No, it hasn't.)

 

The problem with ChatGPT is that its answers are well formulated and appear so plausible, you don't question them.

It seems to depend on what information from the internet you want to believe.

https://www.swimcheck.com/en/city/1005/beaches-wilhelmshaven

 

I'm not an expert on "Wilhelmshaven", but if I Google this I would came to similar insights.

Maybe the problem is that too many false information is out there and an AI cannot easily separate truth from lie.

 

I do not expect 100% correct data from an AI, but a good support in doing tasks.

 

 

[dummzeuch 1506]

30 minutes ago, Rollo62 said:

It seems to depend on what information from the internet you want to believe.

https://www.swimcheck.com/en/city/1005/beaches-wilhelmshaven

 

I'm not an expert on "Wilhelmshaven", but if I Google this I would came to similar insights.

Maybe the problem is that too many false information is out there and an AI cannot easily separate truth from lie.

 

I do not expect 100% correct data from an AI, but a good support in doing tasks.

That's no sandy beach at Südstrand (green grass only) and it's not near the Jadestadion (In my book >5 km does not qualify as "near".) There is a kind of sandy beach further to the east along the Jade Bight, where the second harbour entry used to be. But the nearest real sandy beach is at Hooksiel which is about 15 km to the north from Wilhelmshaven (and ChatGPT also mentions that beach), but you will be hard pressed to find any dunes there either.

Edited January 2, 2023 by dummzeuch

[FPiette 384]

[dummzeuch 1506]

35 minutes ago, FPiette said:

That's not what I read. There are reviewer which will allow or not to enhance the engine. Don't expect your criticism to have an immediate impact. It probably depends on de quality of it and the frequency of the related subject in the questions.

How up to date is your knowledge

 

I was trained by OpenAI using a dataset that was current up until 2021, and I do not have the ability to browse the web or access new information, so my knowledge is limited to what I was trained on. I can still provide general information and assist with many tasks, but I may not have information on more recent events or developments. Is there anything specific you would like to know?

[TigerLilly 16]

ChatGPT does not _understand_ the question, nor does it _understand_ its own answer. ChatGPT tries to detect some kind of pattern, the question fits in and generates an answer, again dpending of patterns. While ChatGPT  is astonishingly good at both, patterns tend to have kind of grey areas where information is not exakt or not right. So it is quite easy to make ChatGPT give complete nonsense answers. So both Nietzsche as well as Beethoven are named as Austrian people. Restricting the question to living Austrians is funny enough:

Tell me some famous Austrian people.

Some famous people who are from Austria include:

    Wolfgang Amadeus Mozart (composer)
    Arnold Schwarzenegger (actor and politician)
    Sigmund Freud (psychologist)
    Gustav Klimt (artist)
    Friedrich Nietzsche (philosopher)
    Ludwig van Beethoven (composer)
    Adolf Hitler (politician)
    Josef Hoffmann (architect and designer)
    Franz Schubert (composer)
    Maria von Trapp (singing family made famous by the movie "The Sound of Music")

Bernd Maierhofer
Living ones!

Sure, here are some famous living Austrians:

    Thomas Klestil (former President of Austria)
    Gerard Mortier (opera director)
    Elfriede Jelinek (Nobel Prize-winning author)
    Michael Haneke (film director)
    Helmut Marko (Formula 1 racing official)
    Andreas Maislinger (founder of the Austrian Holocaust Memorial Service)
    Wolfgang Puck (chef and restaurateur)
    Johann Wolfgang von Goethe (alpine skier)
    Christina Aguilera (singer and actress)
    Alain Prost (Formula 1 racing driver)

Thomas Klestil died in 2004. Johann Wolfgang von Goethe definintely is nor was an alpine skier. So here are 5 answers wrong.

[Rollo62 538]

3 hours ago, TigerLilly said:

ChatGPT does not _understand_ the question, nor does it _understand_ its own answer. ChatGPT tries to detect some kind of pattern, the question fits in and generates an answer, again dpending of patterns.

That is very much true.

So that is the reason I see chatGPT only as tool for generating clever answers, not as 100% precise encyclopedia.

Understanding how it works, it's even more astonishing to see that this AI really evolves a human-like "consciousness", when it comes to philosophical or open questions.

 

I have long time suspected that AI needs some critical mass before it can develop a kind of "consciousness".

The current GPT-3 and ChatGPT clearly point into that direction for me and I think some AI had already passed some Turing tests.

 

It is the "creativeness" that I find particularly interesting, not the "pedantically precision", because such a creative, inspiring tool is suitable for a whole range of tasks.

I'm sure something like Dall-E will transform an entire profession of illustrators, just as DeepL has already done with the profession of translators.
Of course, it's not so desirable to make all creative professions obsolete, but I don't think we'll be able to stop this development anyway.

But I also believe that there may soon be robots in the household and for this the current "understanding" of facts is already more than sufficient.
The only question is how to redefine these answers into actions.

I have looked at a whole series of very well trained GPT-3 chats, which really follow a complete discussion with a kind of "awareness" that they themselves are AI and have limited possibilities.

If it succeeds to cast the already very good answers of the AI into real understanding of facts, then the next step of the AI will be at the front door.
For the reasons mentioned above I doubt that it is already so far.

 

It is still not sure whether the AI can really understand at least something, or only generates very good text patterns randomly.

Only the humans have the feeling that those answers were too good to be random.

Edited January 3, 2023 by Rollo62

[Anders Melander 1795]

People quoting ChatGPT, in the style of "according to Wikipedia", is getting really tiresome.
And as could be expected, some people have also begun using it in discussions to pretend knowledge about topics. Just like they do with Wikipedia. Ask a follow-up question that requires actual knowledge and their arguments fall apart.

 

ChatGPT "knows" language and that's it. It has zero "understanding" of the topics. It has no awareness. It doesn't understand logic or philosophy, nor even know what that is. This isn't a science fiction movie.

Edited January 4, 2023 by Anders Melander

[FPiette 384]

I wrote de demo program showing how to query ChatGPT from your Delphi program. Using ICS of course.

See this post:

 

[Rollo62 538]

1 hour ago, Anders Melander said:

ChatGPT "knows" language and that's it. It has zero "understanding" of the topics. It has no awareness. It doesn't understand logic or philosophy, nor even know what that is. This isn't a science fiction movie.

Thats a fair analysis and I completely agree.

 

But if you see whats possible with those AI, like the LETA series from Dr. Alan Thompson, is really amazing.

He has done a lot of work with various AI's, and knows how to optimize the parameters and prompts.

And yes, its still only a text processor, like an advanced RegEx processor maybe ...  🙂

 

Since chatGPT is even more advanced than LETA, as it may remember older prompts, I expect even much better results.

 

You will always have your point that its only a text processor and not a human, but the chats you can do with those machines are quite inspiring too.

According to the Turing test, a computer can be said to possess artificial intelligence if it can mimic human responses under specific conditions.

If you cannot really proof if its human or an AI in a normal chat, wouldn't it be fair to call the AI somewhat "intelligent" ?

 

What would be your proposal for a proof of creative "intelligence" ?

[Anders Melander 1795]

6 minutes ago, Rollo62 said:

If you cannot really proof if its human or an AI in a normal chat, wouldn't it be fair to call the AI somewhat "intelligent" ?

I don't think so. The Turing test is pointless unless your only goal is to create something that can fool a human and what good is that? We don't need a computer to do that.

 

Trying to define intelligence with too narrow parameters like "it talks like a human" or "it is self-aware" is also not helpful. Intelligence, as observed in most humans and many animals, is many different things the sum of which is what we think of as "intelligence".
The ability to talk like a human, using a database of human knowledge, is really just a party trick and largely irrelevant with regard to Strong AI.

 

I wonder what will happen when the AI chatbots have generated so much output that they predominantly use their own, not necessarily correct, answers as training data...

[Rollo62 538]

18 minutes ago, Anders Melander said:

The ability to talk like a human, using a database of human knowledge, is really just a party trick and largely irrelevant with regard to Strong AI.

I can only say that chatGPT can give really helpful answers and amazing "understanding" of facts, no matter if it really understands or not.

Of course it can have its errors still, but it most of the time completely follows and understands your intentions, even if you ask not so well formed questions or try to trick it somehow by slang language.

 

When you really ask well defined questions about very specific topics, like for example for craftsmen tasks at worksites, how to best solve their tasks in a given situation,

it can give very good advices in 98% of the cases I would say.

This is what I would also expect from a human assistant or teacher and to be honest not many of the shop assistants can help customers questions that adequate.

I would rate chatGPT about 8 and the average, unmotivated human shop assistant 4-6, on a 0-10 scale.

 

Please try chatGPT really out in practice, before you throw it into the "irrelevant" bin so fastly.

I'm very sure that we all have to deal with this kind of AI in the near future, a few years from now.

At least I have a lot of ideas howto use such AI things in the real world.

 

Edited January 4, 2023 by Rollo62

[Rollo62 538]

Just for fun, I've tried to pull some "unsolvable" information out of chatGPT, where I think it has given well suited answers to my questions.

( It remembers that we agreed on the name Assistant a some days before ).

 

Quote

Q:

Hi chatGPT, I would like to know how high a pyramid can get ? Do you know the math behind that calculation of static buildings ?

A:

Hello! I'm Assistant, not chatGPT. However, I can certainly try to help you with your question about pyramids.

The maximum height of a pyramid depends on several factors, including the materials used to build it, the size and shape of its base, and the forces acting on it. In general, the taller a pyramid is, the more unstable it becomes, as the weight of the upper parts of the pyramid puts increasing pressure on the lower parts.

To calculate the maximum height of a pyramid, engineers use principles of structural engineering and mechanics. The most important factor is the ability of the pyramid's base to support the weight of the pyramid. This involves considering the strength of the materials used to build the pyramid, as well as the size and shape of the base. Other factors that can affect the maximum height of a pyramid include wind and seismic forces, which can cause the pyramid to sway or oscillate, and the amount of slope on the pyramid's sides.

 

Q:
I would be interested in the egypt pyramid kind of building, can you please calculate the maximum possible height ?

A:

Sure! The Great Pyramid of Giza in Egypt is one of the most famous pyramids in the world. It is also one of the largest and oldest, with a height of 147 meters (481 feet) and a base of about 230 meters (755 feet) on each side.

The maximum height of a pyramid is ultimately limited by the strength of the materials used to build it and the ability of the base to support the weight of the pyramid. In the case of the Great Pyramid of Giza, the pyramid was built using blocks of limestone and granite, which are relatively strong materials. However, even with these materials, the pyramid's height was limited by the size and shape of the base, as well as the forces acting on it, such as wind and seismic forces.

It's worth noting that the Great Pyramid of Giza is not a perfect pyramid; it has slightly battered sides and its base is not a perfect square. This was likely done to make the pyramid more stable and better able to withstand the forces acting on it.

If you'd like to learn more about the Great Pyramid of Giza and how it was built, I'd be happy to help with that as well.

 

Q:
If you account the same materials as Great Pyramid of Giza, can you estimate the maximal possible dimensions, before a structural break occurs ?

A:

Sure, I can try to give you an idea of the maximum dimensions a pyramid made of the same materials as the Great Pyramid of Giza could have before experiencing a structural failure. However, it's worth noting that predicting the precise dimensions at which a pyramid would fail is a complex task that would require detailed analysis and testing, as there are many factors that can affect the stability and strength of a pyramid.

With that said, some factors that could influence the maximum dimensions of a pyramid made of the same materials as the Great Pyramid of Giza include:

    The strength of the materials: Limestone and granite, the materials used to build the Great Pyramid of Giza, are relatively strong and durable, but they are not indestructible. The maximum dimensions of a pyramid made of these materials would be influenced by the strength of the individual blocks and how they are assembled.

    The size and shape of the base: The larger the base of a pyramid, the more weight it can support. However, there is a limit to how large the base of a pyramid can be before it becomes too heavy to be supported by the pyramid's sides. In general, a pyramid with a wide base will be more stable than a pyramid with a narrow base.

    The slope of the sides: The steeper the slope of a pyramid's sides, the less stable it will be. To increase stability, the sides of a pyramid should have a gentle slope.

    External forces: Wind, earthquakes, and other external forces can also affect the stability of a pyramid. A pyramid that is built in an area with strong winds or a high risk of earthquakes will need to be designed differently than a pyramid built in a more stable location.

Given these factors, it's difficult to predict exactly how large a pyramid made of the same materials as the Great Pyramid of Giza could be before experiencing a structural failure. However, it's likely that a pyramid with dimensions much larger than the Great Pyramid of Giza would be at a higher risk of failure due to the increased weight and stress on the base and sides.

 

Q:

Thanks for the details. Based on the same materials structure of Giza, only scalled to a maximum dimension, can you make en educated guess how large that can get ?

A:

It's difficult to make an educated guess about the maximum dimensions a pyramid made of the same materials as the Great Pyramid of Giza could achieve without more information. The size and shape of the base, the slope of the sides, and the strength of the materials used would all play a role in determining the maximum dimensions of such a pyramid.

However, as a rough estimate, if we assume that the base of the pyramid is a square with sides of length L and that the pyramid has a slope of about 51.85 degrees (the slope of the Great Pyramid of Giza), we can use some basic geometry to calculate the maximum height of the pyramid.

If we let h be the height of the pyramid, we can set up the following equation:

tan(51.85) = h/L

Solving for h, we find that the maximum height of the pyramid would be:

h = L*tan(51.85)

So, for example, if L = 500 meters (about 1640 feet), the maximum height of the pyramid would be:

h = 500*tan(51.85) = 318.5 meters (about 1043 feet)

Again, this is just a rough estimate and there are many other factors that could affect the maximum dimensions of a pyramid made of the same materials as the Great Pyramid of Giza.

 

Q:
With the Pyramid of Giza scaled proportionally to 500m height, how heavy would the whole structure be and how much force will lay on the foundation layer ?

A:

If we scale the Great Pyramid of Giza proportionally so that its height is 500 meters (about 1640 feet), we can calculate the approximate weight and the force on the foundation of the pyramid.

The weight of the pyramid would depend on the volume of the pyramid and the density of the materials used to build it. The Great Pyramid of Giza was built using blocks of limestone and granite, which have densities of about 2.7 g/cm^3 and 2.75 g/cm^3, respectively.

If we assume that the pyramid has the same proportions as the Great Pyramid of Giza and is made of the same materials, we can calculate its weight as follows:

First, we need to calculate the volume of the pyramid. If the base of the pyramid is a square with sides of length L, the volume of the pyramid is:

V = (L^2*h)/3

Substituting L = 500 meters and h = 500 meters into this equation, we find that the volume of the pyramid is:

V = (500^2*500)/3 = 125,000,000 cubic meters

Next, we can calculate the weight of the pyramid by multiplying the volume by the density of the materials used to build it. If the pyramid is made of limestone and granite, we can calculate its weight as follows:

Weight = V * (density of limestone + density of granite)/2 = 125,000,000 * (2.7 + 2.75)/2 = approximately 221.9 million kilograms

To calculate the force on the foundation layer, we need to consider the weight of the pyramid and the size of the base. If the base of the pyramid is a square with sides of length L, the force on each side of the base would be:

Force = Weight/L^2 = 221.9 million kilograms / 500^2 = approximately 887,600 kilograms per square meter

This is just a rough estimate and there are many other factors that could affect the weight and the force on the foundation of a pyramid. However, this should give you an idea of the order of magnitude of these quantities for a pyramid scaled to the size you specified.

 

Q:
Under above conditions, will the foundation layer of granite withstand the forces and pressure in the longterm ?

A:

It's difficult to say for certain whether the foundation of a pyramid scaled to the size you specified would withstand the forces and pressure in the long term without more information. The ability of the foundation to withstand these forces would depend on several factors, including the strength and quality of the granite used, the thickness of the foundation, and the soil conditions beneath the foundation.

In general, granite is a very strong and durable material that is resistant to weathering and deterioration. It is often used as a building material for structures that are subjected to large loads and pressures, such as bridges and buildings. However, the strength of granite can vary depending on the specific type of granite, as well as factors such as the presence of fractures and defects.

The thickness of the foundation is also an important factor in its ability to withstand forces and pressure. A thicker foundation will be able to support more weight and will be less prone to cracking or failure than a thinner foundation.

Finally, the soil conditions beneath the foundation can also affect its ability to withstand forces and pressure. If the soil is weak or unstable, it may not be able to support the weight of the pyramid, even if the foundation is made of strong materials like granite.

Given these factors, it's difficult to say whether the foundation of a pyramid scaled to the size you specified would withstand the forces and pressure in the long term without more information. It would be necessary to carefully analyze the specific materials, dimensions, and soil conditions in order to make a more accurate prediction.

 

Q:
Under above conditions, can you make an estimate of the lifetime of such pyramid, in relation to the current pyramid of Giza ?

A:

It's difficult to make an accurate estimate of the lifetime of a pyramid scaled to the size you specified without more information. The lifetime of a pyramid would depend on many factors, including the quality and strength of the materials used to build it, the weather conditions it is exposed to, and the forces acting on it.

In the case of the Great Pyramid of Giza, the pyramid has stood for more than 4500 years, which is a testament to the durability and strength of the materials used to build it (limestone and granite) and the skill of the ancient Egyptian engineers who designed and constructed it. However, it's worth noting that the Great Pyramid of Giza has also undergone significant conservation and restoration work over the centuries, which has likely helped to preserve it and extend its lifetime.

If we assume that a pyramid scaled to the size you specified is made of the same materials as the Great Pyramid of Giza and is subjected to similar weather and environmental conditions, it's possible that it could have a similar lifetime. However, it's difficult to make a more accurate prediction without more information.

It's also worth noting that the lifetime of a pyramid could be influenced by external factors such as earthquakes, storms, or human intervention. If a pyramid is subjected to strong earthquakes or storms, or if it is damaged or altered by humans, its lifetime could be shortened.

 

 

Ok, the math and results were a little awkward, but tending towards a reasonable direction.

If you consider that this is only a text processor, then this outcome is amazing (at least to me).

To implement some formula and data verifier should be maybe not that hard, to verify hard facts like limestone density, etc.

 

I think the text processor is best if its not trying to answer hard facts and math right now, but this has clearly been an huge evolution to GPT3 1-2 years ago.

 

 

Edited January 4, 2023 by Rollo62

[Anders Melander 1795]

1 hour ago, Rollo62 said:

Just for fun, I've tried to pull some "unsolvable" information out of chatGPT, where I think it has given well suited answers to my questions.

The problem is that you can't use the answers for anything; It's unreliable.

While the answers might sound authoritative you can't trust them to be correct and you would have to research the topic in order to determine if they actually were correct.

https://www.google.com/search?q=how+tall+can+a+pyramid+get

 

If you can't trust it, what good is it? It's like a fully self-driving car that doesn't kill anyone "most of the time".

 

Quote

However, it's worth noting that the Great Pyramid of Giza has also undergone significant conservation and restoration work over the centuries, which has likely helped to preserve it and extend its lifetime.

LOL. A good example of ChatGPT being clueless about the topic it talks about while being very good at talking about it. We got plenty of those already.

[Rollo62 538]

@Anders Melander

Maybe its a question of different expectations ?

1. You might expect answers like from a nobel price winning professor, which is fair enough, so that you can use the data 1:1 as is.

 

2. I would expect answers like from an half-educated sales assistant or a passenger on the street, giving only 25-50% of useful information but leading into the right direction,

    which leads to useful thoughts from where one can search deeper if he likes.

 

For example, from above examples, I was not aware that Wilhelmshaven has a sandy beach nor that it has a Jade Stadion, not that Giza was build from Granite and Limestone.

 

Clearly 1.) is the most desired goal, but 2.) is good enough as a tip-starter for so many cases.

That's why I would'nt say that 2.) is completely useless, I see enough use cases for both options in many fields.

 

I would predict that the answers from 2.) running through a better "data validation" process in the near future will solve most of the issues complained about.

[Dalija Prasnikar 1399]

13 minutes ago, Rollo62 said:

Maybe its a question of different expectations ?

1. You might expect answers like from a nobel price winning professor, which is fair enough, so that you can use the data 1:1 as is.

 

2. I would expect answers like from an half-educated sales assistant or a passenger on the street, giving only 25-50% of useful information but leading into the right direction,

    which leads to useful thoughts from where one can search deeper if he likes.

 

Main problem wit ChatGPT  is that if you are asking about something you don't know well, it can lead you in completely wrong direction and you will never know it because you lack the expertise. And it will lead you there with a confidence of a master. And it is not wrong only occasionally, it is wrong most of the time. If you like wasting your time on wrong leads and hints, then it is absolutely the right tool for any job.

[Rollo62 538]

I'm sure that if you focus on a special problem only and tailoring the questions and prompts very well, you will get reasonable answers.

Ok, not 100% reasonable, maybe 95%, but I have seen very many examples where it works out really well.

This depends on the topics and domains very likely, not in every domain this might work.

Anyway, you have to check out for yourself.

 

I remember well when I've got my first Sinclair Z80, programming one of the first programs, I've programmed a simple Eliza program.

This was very simple basic program of coarse, but from that I realized how easy text processors can lead to interesting Q&A.

And yes, Eliza was completely useless and giving not really helpful answers.

 

The AI developments and technology were sleeping ever since on a low level and only in the last few years some significant, exponential changes happened in that field.

I know the power of exponential growth and that it might show reasonable results soon.

So many people nowadays are getting hot on AI and working on that topic, don't you agree we will see a real chat or human-like AI soon, by fixing the last 5%-10% of issues ?

I do and I don't say that chatGPT is the last step of the evolution, its only the start.

[tgbs 14]

Q. please solve (x+3)^2=25

A. [snip] Calculate the value of sqrt(25) - 3. This will give you the solution to the equation: x = sqrt(25) - 3 = 5 - 3 = 2. In general, the solution to the equation (x+3)^2=25 is x = 2.

Q. isn't x=-8 a solution?

A. No, x=-8 is not a solution to the equation (x+3)^2=25. Because when you put the value -8 of the variable x into the equation, you don't get an equality. Instead, you will get an inequality: (x+3)^2 = (-8+3)^2 = (-5)^2 = 25 The inequality (-5)^2 = 25 is false because the square of -5 is -25, not 25. Therefore, x=-8 is not a solution to the equation (x+3)^2=25. The solution of this equation is x=2 as I told you earlier.

Q. You are wrong. I don't know who taught you math. Please fix: Any negative number squared is a positive number. (-5)^2 = -5.-5 i.e. is 25

A. I'm sorry if I made a mistake. You make an accurate estimate: any negative number squared is a positive number.[snip] However, in the case of the equation (x+3)^2=25, the solution is x=2, as I told you earlier. This equation has no solutions other than x=2. Because when you put the value 2 of the variable x into the equation, you get the equality: (x+3)^2 = (2+3)^2 = 5^2 = 25 The equality (x+3)^2 = 25 is true when x=2

Q. you are wrong x=-8 is also a solution because (-8+3)^2 = (-5)^2 = -5*-5 = 25

A. Sorry my previous explanation wasn't clear. Yes, x=-8 is a solution to the equation (x+3)^2=25. You make a correct argument: (-8+3)^2 = (-5)^2 = 25. This means that the equation (x+3)^2=25 has two solutions: x=2 and x=-8. It is a quadratic equation with two real solutions.

 

But same question now

A.

(x+3)^2=25

√(x+3)^2=√25

|x+3|=5

Now we have two cases to consider:

Case 1: x+3=5 x=2

Case 2: x+3=-5 x=-8

Therefore, the solutions to the equation are x=2 and x=-8.