Make Anything with ChatGPT, Here’s How
HTML-код
- Опубликовано: 21 авг 2024
- If you're serious about AI, and want all of my code, join my community: www.skool.com/...
Follow me on Twitter - x.com/DavidOnd...
Please Subscribe.
With ChatGPT and Python you can make literally anything. This video will teach you how.
🔥 I'M HIRING! Do you want to join my team? Apply here: forms.gle/DWUxTENdet7CeiEi7
I used a different email than the one linked to this account, but I definitely sent in an application 🤘🤖
What time zone are you in?
after a successful day you look in the mirror and the reflection tells you: "I love the chaotic evil vibes of Nox! The human flash moments really capture the intensity. Fear no evil, even with the shadows of alcoholism. Embracing the devil within, I find the keys to Kabbalah revealing the true essence of darkness. Incredible work!" If I am right with that, you are like me. And I have send you an application.
Oh Looks Mysterious hmm
Heyyy David! I’ve applied today!
I actually asked ChatGPT4 recently, how could I create a email marketing software, and I learned so much.. it mentioned I should start a python flask application, but after reiteration mentioned that I should use the high-level python framework Django, and I also would use and need to know react router implementation.
So of course I haven’t yet tried this project, but AI certainly makes me feel more confident about trying to attempt to code something.
You are doing exactly what I do when using ChatGPT. The thing is, you can't use ChatGPT if you don't know a bit of the field you are trying to use. Sometimes it can rush through something or skip some parts and it takes a sharp, attentive mind to spot those weird parts. Sometimes it takes a reconstruction of the question you ask to get the right answer you are looking for. So I can confirm that all the things you said in this video are true. The AI is smart in a way that it can be misleading and disastrous if you don't know what you are doing.
"it predicted dog... our model is quite shit" -- felt the disappointment there😂...but this is cool stuff 😎
🎉😂 BEST COMMENT AWARD!🏆🫢
Ok so, for people reading comments, DO NOT install Python on your personal computer unless you’re a developer. Instead, use a virtual machine to set it up, like Virtual Box or VMware.
Doing so, you will prevent many incoveniences that could happen while installing packages. You’re welcome.
Is pyevv or conda not good enough?
Even with them have dramas sometimes but wondering what your train of thought is on this, I'm pretty new still
Wait why, what are the inconveniences, are you risking erasing your own system, or getting hacked?
Instead, I recommend using Docker to contain this project, and it's fairly easy to use.
Or just learn to use anaconda environments was super easy when I knew nothing
@@FloodGold docker was always using alot of cpu and taking ages to load things when i tried using it, to the point where the waiting around wasnt worth it, got onto poddman but even then, for smaller personal stuff i diddnt feel like the required time/cpu was worth it that much.. is that an uncommon thing or just because of a potato laptop? i71050
Tip: instead of repeatedly asking it to explain it in “plain English”. Ask it to make it easier to understand or explain in more detail.
Plain English just means the English language
Bring more videos about this! Low Code, software creation with ChatGPT. My only request is to build something really useful, that you could sell as a SaaS or something that we can apply in our daily lives.
Man these long videos are amazing, thank you
Regarding the speed...I feel it is essential to understand that there are (at least) two categories of speed: internal and external. You can call it input processing and output bandwidth or whatever. They explain it all on both the marketing page - which is not to be trusted - and their (somewhat) legally binding ChatGPT info sites for account, upgrade, etc.
The model is about 2x as fast for...whatever it does to process input. I think inference has not changed. Because they themselves say, it is not more intelligent than before. I guess it is all sorts of "wiring" that was improved. Stuff that caused overhead.
That is the internal part. That changes with the model used.
But it also has 5x the rate limit as compared to GPT-4 Turbo. That's external speed. Rate limit is artificial throttling. It is done to save energy. To save money. They could have given you this rate limit from the start, but they didn't have Microsoft's money to do that. Possibly also not the backend to handle that. But that has NOTHING to do with the model itself. They just put the brakes on the model output.
I don't KNOW this to be true, but that is how I understand it and it makes sense to me.
Which would mean that, to make this part of the benchmarks is...utter nonsense.
I like how you gave us a tutorial on how to use these tools in a practical way!
Everyone should be making agents. Everyone should be making resumès for their agents.
I have Hermes Theta, LlaVa 1.6, Nomic embedding, Whisper, and Bark laced down pretty tight on a laptop that will be woefully obsolete the second an AI agent hits the mainstream in a meaningful way. Anyone can do this and everyone should. Anyone who does will steamroll over everyone who doesn't.🤘🤖
Bro pls english i don't understand the technicalities😅
@@Paritosh___ these are open source models you can run on consumer hardware. I have a whole 16gb and no GPU, so I've been working with small models. I've picked up a lot of tricks and my data pipelines are pretty clean now.
Here's a high level overview of my chain, by model:
* Hermes 2 Theta Llama 3 - best Llama 3 8B fine-tune. OpenHermes models have been consistently excellent open source models. This is the latest one, built on Llama 3, and it has extra training and special tokens for JSON output, which means it can label its own responses, assign a tool with a response simultaneously, tons of fun stuff. This is my main model.
* Nomic - embedding models, coupled with a vector store are basically a memory librarian. It sorts texts by semantic similarity. If you chunk up everything that enters your app, it will return the most semantically similar text to use as context to answer your prompt - or - RAG.
* LlaVa - Vision model. This can understand pictures you feed it, or screenshots of videos or your desktop. This can add a lot of functionality and also scrape pages that can't be scraped by other methods.
* Whisper/Bark - Text to Speech and Speech to Text models. More specifically, I use faster-whisper. Bark is a personal preference because it can be prompted to generate other sounds besides speech pretty easily.
I have them all stitched together using primarily Ollama. I use the tools from CrewAI and Langchain, but I use my own agent framework.
@@Paritosh___ I'm using Ollama and tools from CrewAI and Langchain. I don't use either one's framework, I like to DIY my own agent chains in functions.
My primary model is Hermes Theta because of Nous Research's track record with OpenHermes, and it also comes with extra tokens to force a JSON response, which is handy for function calling and context classification.
LlaVa is a vision model and can see my desktop at all times.
Nomic is my embedding model for RAG
Whisper/Bark is my Speech-to-speech pair. Specifically faster-whisper. Bark is a personal preference because it can generate other sounds besides speech pretty easily.
They all work together as a general copilot.
I've tried to explain my agent chain twice and yt is deleting it for some reason. I made a copilot with open source models. It's greatly enhanced my life.
Would the llava phi 3 be better then the original there is also the llama 8b llava , are they better?
I was about to give up on coding man. You saved me im now so invested in AI. Shout out from Cape Town , South Africa
In less than a decade there will be no programer cause ai will do the coding.
@@Mehrdadkh87 which is why you must build Ai agents now.
@@Mehrdadkh87 professional programmer/developer here. I work in industrial advanced systems. Many people have the same misunderstanding about computer code in general. I would like to give more insight into it if I may. I know many famous tech leaders are making bold statements on this topic, but unfortunately they don't provide enough details. You can think of the code generated by a neural network in a similar way to a story written by the same model. The story will have a certain structure to it and this structure is the result of both system prompts (the prompts you dont see) and the training data. Does this mean it is a bad story? No. But it is in essence, a story encapsulated in a bubble of pre-defined rules. This has no problem whatsoever unless you are trying to make something out-of-the-box. The main goal of software development in general is to automate things on a computer, in a way that it will reduce the manual labor. The programming languages exist to combine our natural thoughts and mathematical strictness into a single entity. We can not take away either of these two, otherwise, everything we build in the modern technology would collapse. Many people outside the field, or people that are too obsessed with a programming language, a set of tools, etc. generally tend to show strong fear when faced with a better tool. ChatGPT is the better tool here in many aspects. Why? Well, ChatGPT is an interface to the GPT models, and these models are some of the strongest in the world. They have been trained on vast amounts of data and a lot of effort was put into it. In order to make a better GPT in the future, you can not simply prompt it into the current GPT. This is against the laws of the nature. In order to create something better, we need a combination of tools and knowledge. ChatGPT was built heavily using Python as a programming language, and lots of ML libraries such as PyTorch. Now ChatGPT can WRITE PYTORCH itself! But how? Simple. Because computer code in essence is text content, and when you have a model trained on text content, you should be able to generate more of it. This means you can generate similar content to your training data, create heavily modified versions of it, create non-existent content from billions of combinations of it, create unique patterns , etc. But we have some big problems here. The biggest one is, these state-of-the-art AI models are not intelligent entities. They do not have the ability to make decisions, think, understand or reason. I know it looks like they do all of these, but in reality it is a big circus of estimations and this is fine. What is not fine, is , we can not replace humans with it. It would be like replacing humans with a dishwasher. We can not replace writers, programmers, mathematicians, artists, scientists etc. with an NLP model. For example programming, is not the code, not the syntax, not the operating system, and not the UI of your desktop. Programming could be done with a set of emojis, sticks, bubblegums, if it would be more efficient. The purpose of creating software with code, is to make sure we specified thousands of details that are important to us, turned them into electrical signals, put a lot of logic into it, and make sure we get the results we want from the computer, when we want. We first tried to make it more like english because why not. We failed because then we forgot to add the amount of mathematics and logic we needed into it. We quickly remembered why we had mathematical symbolism in the first place. It was to strictly explain things, in a short but meaningful manner. Then we said, well, let's combine english with symbols and then we will have a toolset that is useful. It worked! We figured out that sometimes we can use a more english-like syntax (such as python, basic etc) and sometimes (when needed) use a more complex way of writing our logic, which takes us to C/C++, Assembly languages, and more. We actually created Python itself, using C! How crazy right? Then we said well, perhaps we should make it even easier for repetitive tasks, and created pure simple tools for everyone to use to create websites, simple apps and get their work done. We made website builders that needed NO CODE AT ALL. We have Excel, Google, etc. Why? To not spend time over and over again on same things. But wait, did we stop using C/C++ or Assembly just because we created Python? No. Did we stop creating very low level code that is too hard to understand? No. Did we stop welding wires just because we already did it before? No. Because we still need to do things with them, to create better versions of the things we already made. Do we still do everything with C? Never. Do we write a lot of C everyday? Yes, when we need to, and sometimes to train our brains, which in return provides us with better ideas and makes us realize more details. These days, I use 4-5 AI chatbots as I write my code. I write certain logic in a mathematical syntax, and sometimes in a specific programming language syntax, and add natural language statements to it. The chatbots generate me all the boilerplate I need and I only need to make small changes in very specific details. These details can only be seen if you know a lot about the thing you are doing within the code. This is also a reason to be able to read, write, understand computer code in different languages if you are dealing with code in your daily life even if you don't write it all the time. What I assume for the future (near) is that we programmers will be more of supervisors. Downside is, we will be under much more stress, always making sure the AI didn't make a small mistake that can collapse the whole system we spent years on. Most probably we will be using mathematical symbolism and natural language expressions in a much much more simple way and it will not look like the code we write today, will be much shorter and brief. When we implements chips into our brains, we will only imagine concepts and generate instant outputs. The funny thing is, we still need to know a lot about advanced logic, mathematics, symbolism, how to think properly for strict concepts like computing or planning. These may seem simple at first, but believe me, even after long years, I still crave more and more of detailed strict mathematical logic in my work. You can never get enough of it. Therefore, if you learn how to build tetris without using a library and using only fundemental tools such as C/C++, you will learn much much much more than just tetris or C/C++. You will learn how to think like a tetris-maker (lol). But if you copy-paste the code from someone else, or a chatbot, you will never learn how to think like a tetris-maker. Will tetris earn you money? no. Will people respect you for it? no. Will you become a super cool master of programming? no. BUT you will have a new power. This new power will lead you to a new idea. this will continue forever. So, this comment turned into an essay for some reason. Anyways hope more people read this.
@@Mehrdadkh87 professional programmer/developer here. I work in industrial advanced systems. Many people have the same misunderstanding about computer code in general. I would like to give more insight into it if I may. I know many famous tech leaders are making bold statements on this topic, but unfortunately they don't provide enough details. You can think of the code generated by a neural network in a similar way to a story written by the same model. The story will have a certain structure to it and this structure is the result of both system prompts (the prompts you dont see) and the training data. Does this mean it is a bad story? No. But it is in essence, a story encapsulated in a bubble of pre-defined rules. This has no problem whatsoever unless you are trying to make something out-of-the-box. The main goal of software development in general is to automate things on a computer, in a way that it will reduce the manual labor. The programming languages exist to combine our natural thoughts and mathematical strictness into a single entity. We can not take away either of these two, otherwise, everything we build in the modern technology would collapse. Many people outside the field, or people that are too obsessed with a programming language, a set of tools, etc. generally tend to show strong fear when faced with a better tool. ChatGPT is the better tool here in many aspects. Why? Well, ChatGPT is an interface to the GPT models, and these models are some of the strongest in the world. They have been trained on vast amounts of data and a lot of effort was put into it. In order to make a better GPT in the future, you can not simply prompt it into the current GPT. This is against the laws of the nature. In order to create something better, we need a combination of tools and knowledge. ChatGPT was built heavily using Python as a programming language, and lots of ML libraries such as PyTorch. Now ChatGPT can WRITE PYTORCH itself! But how? Simple. Because computer code in essence is text content, and when you have a model trained on text content, you should be able to generate more of it. This means you can generate similar content to your training data, create heavily modified versions of it, create non-existent content from billions of combinations of it, create unique patterns , etc. But we have some big problems here. The biggest one is, these state-of-the-art AI models are not intelligent entities. They do not have the ability to make decisions, think, understand or reason. I know it looks like they do all of these, but in reality it is a big circus of estimations and this is fine. What is not fine, is , we can not replace humans with it. It would be like replacing humans with a dishwasher. We can not replace writers, programmers, mathematicians, artists, scientists etc. with an NLP model. For example programming, is not the code, not the syntax, not the operating system, and not the UI of your desktop. Programming could be done with a set of emojis, sticks, bubblegums, if it would be more efficient. The purpose of creating software with code, is to make sure we specified thousands of details that are important to us, turned them into electrical signals, put a lot of logic into it, and make sure we get the results we want from the computer, when we want. We first tried to make it more like english because why not. We failed because then we forgot to add the amount of mathematics and logic we needed into it. We quickly remembered why we had mathematical symbolism in the first place. It was to strictly explain things, in a short but meaningful manner. Then we said, well, let's combine english with symbols and then we will have a toolset that is useful. It worked! We figured out that sometimes we can use a more english-like syntax (such as python, basic etc) and sometimes (when needed) use a more complex way of writing our logic, which takes us to C/C++, Assembly languages, and more. We actually created Python itself, using C! How crazy right? Then we said well, perhaps we should make it even easier for repetitive tasks, and created pure simple tools for everyone to use to create websites, simple apps and get their work done. We made website builders that needed NO CODE AT ALL. We have Excel, Google, etc. Why? To not spend time over and over again on same things. But wait, did we stop using C/C++ or Assembly just because we created Python? No. Did we stop creating very low level code that is too hard to understand? No. Did we stop welding wires just because we already did it before? No. Because we still need to do things with them, to create better versions of the things we already made. Do we still do everything with C? Never. Do we write a lot of C everyday? Yes, when we need to, and sometimes to train our brains, which in return provides us with better ideas and makes us realize more details. These days, I use 4-5 AI chatbots as I write my code. I write certain logic in a mathematical syntax, and sometimes in a specific programming language syntax, and add natural language statements to it. The chatbots generate me all the boilerplate I need and I only need to make small changes in very specific details. These details can only be seen if you know a lot about the thing you are doing within the code. This is also a reason to be able to read, write, understand computer code in different languages if you are dealing with code in your daily life even if you don't write it all the time. What I assume for the future (near) is that we programmers will be more of supervisors. Downside is, we will be under much more stress, always making sure the AI didn't make a small mistake that can collapse the whole system we spent years on. Most probably we will be using mathematical symbolism and natural language expressions in a much much more simple way and it will not look like the code we write today, will be much shorter and brief. When we implements chips into our brains, we will only imagine concepts and generate instant outputs. The funny thing is, we still need to know a lot about advanced logic, mathematics, symbolism, how to think properly for strict concepts like computing or planning. These may seem simple at first, but believe me, even after long years, I still crave more and more of detailed strict mathematical logic in my work. You can never get enough of it. Therefore, if you learn how to build tetris without using a library and using only fundemental tools such as C/C++, you will learn much much much more than just tetris or C/C++. You will learn how to think like a tetris-maker (lol). But if you copy-paste the code from someone else, or a chatbot, you will never learn how to think like a tetris-maker. Will tetris earn you money? no. Will people respect you for it? no. Will you become a super cool master of programming? no. BUT you will have a new power. This new power will lead you to a new idea. this will continue forever. So, this comment turned into an essay for some reason. Anyways hope more people read this.
Finally some fresh air after the google/apple fanboys out there
40:20 yo my boy unlocked the secrets of life. Paralysis by analysis people out here watching hours of learning videos thinking they are putting in positive hours, only to forget 70% of it by next week
Just discovered you, my boy. You're a goddamn G!
Thanks very much David. Huge fan of your content.
Very helpful video. thank you. 👌🏼
Havent even seen the video, but i love the idea of it so much that you earned a subscriber, like and comment. Really thoughtful topic.
could you please tell me what do you think about Devin AI, a new software engineer???
This is a seriously impressive tool..
Thanks for the video! Ur brilliant and hilarious 😂
Can you Make a video on Best OBS Recording Setting?
amazing, keep the good job
5000 a month, you got to be kidding me, if you want me to make you rich, you got to put at least ten times that on the table. If you do, I'd be happy to accommodate you.
Bro built a gym management system am struggling with that while using chat gpt i have no coding experience
i have dome small prodjects but big ones get me stuck... cause i dont know python :D
I think you just need to train it overnight or something. It should work good.
It's okey
Hey mate;. Is it too late to throw my hat in the ring for that job?
"Not hotdog".
"You will not get anywhere by constantly watching videos"...Why are you attacking me?😭😭😭😭
gpt4o better than claude in cooding?
How to embed in WP site?
warum hast du immer ein Pflaster auf der Nase ?
helps me breathe
I am French so I don't understand very well and I have a beginner level so I would like gpt to redo this tutorial for me, it is aimed at a beginner and above all to answer all my questions But it's tutorials are very bad, I think I'm using it wrong
😎🤖
cat's aint better
Paid version is too detailed which is annoying 😂
😮
creat an ai agent
You are all over the place. You should be a bit more focused on your videos. Do you watch what you produce. Sorry but I’m not encouraged at all to try coding
whats on ur nose ? why u put it there
Man, what happened to your nose ?
He is just like to wear this
He uses it to help him breathe hehe
If ur learning dont use chatgpt...
False. Use it as a tutor.
@@InnocentiusLacrimosa to each their own, you may want to learn about ur trivial math but it sucks
@@RoqueMatusIII Having worked in education and also in coaching, I truly do think that AIs will (already do) enhance our learning processes. There is nothing noble about going through badly designed documentation or internet forum answers line by line instead of asking context specific questions on how to approach some specific issue. The speed of learning through more focused and relevant advice is a very important quality in the process of learning.
@@InnocentiusLacrimosa Ai sucks, plus I use much better systems like RemNote, and Forest App. These applications already do alot of things that are backed up by years of nueroscience.
God deals with each one of us on a personal level. God is dealing with me, apparently God gave me something? Believeth network Fisher Amen I do not link it for this. But AI will fail and take us with it or we stand up now and stake our ground in the AI world as Christian's. I do not want your money but I have a fully functional already paid for foundation that could really use your assistance. Many more too. LoveYou!!!
went with perplexity pro and there is a year paid, $400 Ty, SIr
I am extremely interested in joining your team could we talk?