Discussing the article: "OpenAI's ChatGPT features within the framework of MQL4 and MQL5 development"
The article Opportunities of OpenAI's CHATGP in the context of MQL4 and MQL5 development has been published:
Author: Evgeniy Ilin
There are not enough citations of promts. It is not clear from the text how ChatGPT queries were set.
For example, I never managed to get the code of opening positions for 5ka. It kept returning a ticket instead of a boolean variable.
double calculateEMA(int PeriodEMA,double Flatness=2.0,int Shift=0)
is incorrect. This approach does not work with exponential average. For correct calculation of the EMA you need 10-20 times more bars than the MA period. And how does it feel to constantly run such a cycle in the Expert Advisor?
And in general, guys, stop talking about indicators. They do not carry any "unnecessary and redundant calculations and functionality".
There are not enough promt quotes. It is not clear from the text how the ChatGPT requests were made.
For example, I never managed to get the code of opening positions for 5ka. It kept returning a ticket instead of a boolean variable.
Perhaps I should have emphasised that prompts are not important. He understands everything. Everything here is empirically achieved. Besides, I wrote that everything must be double-checked and then corrected. He doesn't give working code in all cases, and you have to modify it. I'm sure I'll sit down and make it work. Don't get hung up on prompts, it's not a poem you need to memorise.
And in general, guys, stop talking about indicators. They do not carry any "unnecessary and redundant calculations and functionality".
You'd better think about the fact that the starting EMA calculation is not equal to the subsequent ones, because you need to save bars until you are blue in the face, and you need to trade here and now. About the cycles, everything works by bars, I didn't notice any noticeable slowdowns. You can finalise the calculations as you want for this indicator, but will it give you much ) I just know that nothing at all ).
Maybe I should have emphasised that proms don't matter. He understands everything. Everything here is empirically achieved. Besides, I wrote that everything should be double-checked and then corrected. He doesn't give working code in all cases and you have to modify it. I'm sure I'll sit down and make it work. Don't get hung up on prompts, it's not a poem you have to memorise.
I guess I have a different opinion. For gpt it is the right questions that are important. The article seems to be in terms of meaning and title, how to ask Promt the right questions to get the most correct code, but in fact simple indicators.
I will tell you this, I sat down and started to try simple and everything became clear at once. When you practice enough, you will realise that it's not about Promt at all. I have never once used someone else's prompt, communicated stupidly as a person and got exactly what I asked for. I just do it and I get it. I honestly don't understand where the problems come from. The structure of your thought is important, conciseness, blockiness. If you think correctly, you start asking the right questions. It takes practice. I can fill an article with prompts and it will be 2 times bigger, but if there is no what I said it is like memorising a formula in maths, you have the formula but no understanding.
I'll tell you this, I sat down and just started trying and everything became clear right away. When you practice enough, you'll realise that it's not about prompts at all. I have never once used someone else's prompt, communicated stupidly as a person and got exactly what I asked for. I just do what I do and I get it. I honestly don't understand where the problems come from. It is important the structure of your thought, conciseness, blockiness. If you think correctly, you start asking the right questions. It takes practice. I can fill an article with prompts and it will be 2 times bigger, but if there is no what I said it is like memorising a formula in maths, you have the formula but no understanding.
Yes, as if without pretence, just dissonance arose from the expected by the title of the article and the content. I hoped that your practice of promtov something new))))))
I practice regularly, and I would not say that it is an easy topic, to set the promt as necessary. And often it goes round in circles and the problem is not solved, especially for 5k. For simple tasks, and even not known norms, and for algorithms by the way, too, the logic is sufficient.
No complaints, just a dissonance from the expected by the title of the article and the content. I was hoping that your promt practice would give something new))))
I practice regularly, and I would not say that it is an easy topic, to set the promt as necessary. And often it goes round in circles and the problem is not solved, especially for 5k. For simple tasks, and even not known norms, and for algorithms by the way, too, the logic is sufficient.
Well about prompts neither in the title nor in the description. When I wrote I did not give examples as a matter of principle, because it's all individual and everyone's way of thinking is different. Each dialogue is unique and each task is a little different, that's why it is so important to develop your own methodology. My task was to pass on my experience and to teach more about the right attitude to this kind of tool. Because as always many people want everything at once, and then they invent a lot of things for themselves and start broadcasting them to others, although it is only their thoughts. But I think within the framework of the discussion of the article we can solve examples, why not. Let me try to help you with the solution of your problem, there will be prompts for you.
Well about prompts neither in the title nor in the description. When I was writing I did not give examples as a matter of principle, because it's all individual and everyone's way of thinking is different. Each dialogue is unique and each task is a little different, that's why it is so important to develop your own methodology. My task was to pass on my experience and to teach more about the right attitude to this kind of tool. Because as always many people want everything at once, and then they invent a lot of things for themselves and start broadcasting them to others, although it is only their thoughts. But I think within the discussion of the article we can solve examples, why not. Let me try to help you with the solution of your problem, there will be prompts for you.
It would be good) as part of sharing experience) the task is complicated by the fact that µl doesn't know gpt languages very well. Sometimes it is quite difficult to get error-free code.
It is almost impossible to get it without errors at all. This is especially true for GPT 3.5. The fourth one is better. There are always some defects. Emku is the same C++, it produces everything normally. I used it for C# and I can't say it's much better. You just have to think that it is not worth assigning responsible tasks to it, if only to save time, so it gives you a rough sketch and then correct it anyway. I use it more instead of Google, mostly for short algorithms or regular expressions, which saves me time. Or, for example, I am too lazy to think up some algorithm, I ask him to do it and then I polish it for me, I have an example right away. Everyone is used to searching in Google, and he has what you need at once. In general, it's like this. Those who do not know how to code want to build their own owl is definitely not here ))))
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
You agree to website policy and terms of use
Check out the new article: OpenAI's ChatGPT features within the framework of MQL4 and MQL5 development.
In this article, we will fiddle around ChatGPT from OpenAI in order to understand its capabilities in terms of reducing the time and labor intensity of developing Expert Advisors, indicators and scripts. I will quickly navigate you through this technology and try to show you how to use it correctly for programming in MQL4 and MQL5.
I think that when people learn about this kind of technology, they all start to fall into roughly three subgroups:
I began to get acquainted with this technology a long time ago and at the beginning I belonged to the third category. In the first two days of dealing with this AI, I abruptly moved from the third to the first category, after which a more interesting and rather unpleasant process of adjusting my own beliefs began, which is more like a rollback to the "1.5" category, which is already a more realistic assessment of this technology.
This technology is useful, but not as much as you might initially think. In this regard, it is worth paying tribute to the developers and marketers of this technology, if only for the fact that it creates an incredible "wow" effect from use in the first couple of days, which is enough for a chain reaction of self-promotion.
To understand this, you need a lot of practice in dealing with this AI. Personally, I had about a hundred different dialogues with it on various topics. I can say that I have gained enough practice in using this technology to start using it for MQL5. Before moving on to practical applications, I just need to tell you some very important information, and for this we will need to look deeper under the hood of this technology.Author: Evgeniy Ilin