AICodeKing
AICodeKing
  • 90
  • 517 959
Maestro + Qwen2 + DeepSeek-Coder-V2 : Generate APPLICATIONS with ONE PROMPT (FREE, LOCAL & FAST)
In this video, I'll be telling you that how you Generate Applications with Local AI Model Agents. This way you can do Text - To - Applications for free and locally. In this video, I'll be using Maestro combined with Qwen2 and DeepSeek Coder model via Ollama. This way you can outperform Claude-3.5 sonnet while being free. We'll make agents and sub-agents with these models and we'll be generating Games, Websites, Applications and much more in this video and figuring out which model configuration works best for local usage. You can also do Text-To-Frontend, Text-To-Application and other things with this. This Maestro tool can also be used with any opensource LLM, OpenAI models or the other Claude models such as GPT-4O, Claude-3, CodeQwen, Mixtral 8x22b, Mixtral 8x7b, GPT-4, Grok-1.5 & Gemini Code Assist.
-------
Resources:
Maestro Github Repo : github.com/Doriandarko/maestro
------
Key Takeaways:
📌 Revolutionary AI Creation: Discover how Maestro with Claude-3.5 Sonnet allows you to create apps like Desktop Apps, Web Apps, and Games with a single text prompt, using innovative AI Agents technology.
💡 Agent-Based Framework: Learn about the powerful agent-based framework where the Orchestrator LLM breaks down tasks, Sub-Agent LLMs handle execution, and the Refiner LLM ensures quality, providing seamless AI development.
💰 Cost-Effective Local LLMs: Explore the benefits of using local LLMs like DeepSeek Coder and Qwen, reducing API costs while maintaining high performance with the Maestro framework's flexibility.
⚙️ Step-by-Step Configuration: Follow our detailed guide to configure and install Ollama models, DeepSeek Coder V2, and Qwen2 72B, ensuring you set up your AI environment correctly and efficiently.
🎮 Creating a Snake Game: Watch as we demonstrate creating a Snake game using HTML, CSS, and JS, comparing results between Claude and local models, showcasing the potential of different AI configurations.
🌟 High Customizability: Understand the extensive customizability of the Maestro framework, allowing you to mix and match models from Anthropic, Gemini, and OpenAI to tailor your AI projects to specific needs.
👍 Viewer Engagement: Engage with our content by sharing your thoughts in the comments, liking the video, subscribing to the channel, and using the Super Thanks option to support further innovative AI content creation.
--------
Timestamps:
00:00 - Introduction
00:12 - About Maestro (Text-to-Application with Agents)
00:30 - About Agents
01:04 - Using it with Local LLMs
01:40 - Installation
03:40 - Using just the DeepSeek-Coder-V2 model leads to FAILURE
04:33 - Replacing DeepSeek-Coder-V2 with Qwen2 as Orchestrator
05:36 - Insane Results Outperforming Claude-3.5-Sonnet
07:53 - Conclusion
zhlédnutí: 3 350

Video

GPT-Artifacts + DeepSeek-Coder-V2 : BEST Text-To-Frontend Tool with Local LLM Support! (with Ollama)
zhlédnutí 2,4KPřed 2 hodinami
In this video, I'll be telling you that how you can setup a Claude-Like Artifacts feature locally that works with Ollama Models. You can generate Fully-working Applications, Frontend & UI Components with it in seconds. I'll be configuring it with DeepSeek-Coder-V2 Model. That means you can use it for free. It can also generate frontend in almost any language like Tailwind, NextJS, Svelte, JSX, ...
Maestro + Claude-3.5-Sonnet : Generate any APPLICATION with ONE PROMPT (powered by Claude-Agents)
zhlédnutí 8KPřed 4 hodinami
In this video, I'll be telling you that how you can do Text-To-Application, Frontend, Backend & Anything you can imagine with Claude-3.5 Sonnet based Agents. You can generate any application you want with just One Text Prompt. To do this we'll use Maestro Agent System. You can get it setup immediately and do Text-To-Frontend and Text-To-Application in seconds with Claude-3.5 Sonnet. This Maestr...
Claude-3.5 Sonnet + Qwen2 + ContinueDev : This AMAZING Coding Copilot BEATS Github Copilot & Others!
zhlédnutí 9KPřed 7 hodinami
In this video, I'll be telling you that how you can create a new coding copilot / assistant with ContinueDev, ShellGPT & the New Anthropic Claude-3.5 Sonnet Model. This new Anthropic Claude-3.5 Sonnet model based copilot is cheaper and better than Github's Copilot & every other local, opensource copilot I have ever seen. This Github Copilot alternative can work even without the need of GPUs whi...
Claude-3.5 Sonnet : This NEW & BEST Model beats GPT-4O, Gemini 1.5 Pro, Llama-3 400B & Claude-3 Opus
zhlédnutí 3,4KPřed 9 hodinami
In this video, I'll be talking about the recently released Claude-3.5 Sonnet. This is a new model made by the team of Anthropic which is beating each and every other closed-source and open-source model. It beats GPT-4O, Claude-3 Opus, Gemini 1.5 Pro & Llama-3 400B. This is the best model I have seen. In this video, I'll also be testing it out and finding out if it's any good. They have also rel...
DeepSeek-Coder-V2 + ContinueDev + ShellGPT : The FREE & BEST LOCAL COPILOT EVER! (works without GPU)
zhlédnutí 10KPřed 14 hodinami
In this video, I'll be creating an amazing Github Copilot Alternative with the new DeepSeek-Coder-V2 model. To do this I'll also be using the ContinueDev VSCode/NeoVim extension. I'll also be using the ShellGPT program to create a shell copilot as well. I'll also be utilizing the Free 5M Tokens API given by Deepseek. That means you can use it as a copilot for free and you don't need any GPUs to...
DeepSeek-Coder-V2: The NEW & BEST CODING MODEL is here! (beats GPT-4O, Gemini, Codestral & Claude-3)
zhlédnutí 7KPřed 16 hodinami
In this video, I'll be covering the newly released Opensource DeepSeek-Coder-V2 which is an amazing new coding-focused opensource model that beats GPT-4O, Codestral, Claude-3 Opus, GPT-4 Turbo, Qwen-2, Llama-3, Gemini 1.5 Pro in almost all benchmark. This is a new game changer Mixture-of-Experts (MoE) model that is small and amazing in Coding! You can use it as a Github Copilot alternative with...
How to choose the "Best AI Laptop" (Mac, Windows & Linux)
zhlédnutí 2,1KPřed 19 hodinami
In this video, I'll be discussing what you need to consider before buying a laptop for AI purposes, including local inference, LLMs, and text-to-image models like Stable Diffusion 3 (SD-3). I'll cover key aspects such as which CPU you should consider-whether it's Apple's M4, Snapdragon X, or Intel/AMD CPUs. We'll also dive into GPU options, comparing Nvidia, Apple, Intel, and AMD GPUs. Furtherm...
MinimalChat : STOP PAYING for ChatGPT with this NEW, EASY & LOCAL Alternative!
zhlédnutí 2,9KPřed 21 hodinou
In this video, I'll be telling you about a new, local and self hosted ChatGPT that is amazing and super easy to install. It utilizes the new WebLLM method to directly load LLMs in your browser. You can also use it with Ollama, Groq, OpenAI, Qwen2 and other such providers. You can get started with it in seconds just like ChatGPT. This alternative is much better than ChatGPT. It works with Ollama...
LSP-AI : This New LSP based Coding Copilot is LOCAL, FREE & Amazing! (works w/ Ollama & OpenAI)
zhlédnutí 4,9KPřed dnem
In this video, I'll be talking about LSP-AI which is a Github Copilot alternative that is Free, Local and Opensource. I'll be telling you that how you can set it up with Llama CPP, Ollama, Groq, OpenAI. We'll be using StableCode Model, Qwen-2 model as well as Llama 3 and GPT-4O model. I'll be trying out each and every LLM with this Opensource Github Copilot Alternative. This alternative can als...
Gemini-UI-To-Code : This Gemini Frontend & UI Generator is FREE & Amazing! (OpenUI & v0 Alternative)
zhlédnutí 9KPřed dnem
In this video, I'll be telling you that how you can generate Frontend & UI Components easily with Google's new Gemini 1.5 Pro & Flash Model. We'll be using the Gemini UI To Code opensource repository to achieve this. Google also gives you a free tier for their API. So, use can effectively use it for free. This is based on a Streamlit interface which means it is extremely customizable. It can al...
You should switch to Opensource, Right now! (Ft. Recall & Adobe)
zhlédnutí 1,2KPřed dnem
In this video, I'll be talking about the recent Windows AI Recall Privacy nightmare and the Adobe's new change in ToS which allows them to use any user's content to train their AI models. This includes all users who use any Adobe products like Photoshop, After Effects and anything. I'll also be discussing that how you can make a switch from all this privacy nightmare to opensource alternatives ...
Stable Diffusion 3: Open Weights for SD-3 is now Available! The Best Text-To-Image Opensource Model
zhlédnutí 2,1KPřed dnem
In this video, I'll be talking about the recently released Stable Diffusion 3 model. This model throws every other model like Midjourney into the water. This is an opensource model. We'll be checking it out in this video. You can easily use this Text-To-Image model to replace Midjourney and stop paying for that. Key Takeaways: 📢 Big News: Stable Diffusion 3 Weights Released! Stable Diffusion ha...
Apple Intelligence is Cool? (Copilot, Privacy, Custom Models & Easy-to-build AI Apps)
zhlédnutí 856Před dnem
In this video, I'll be talking about the recent announcements from Apple's WWDC 2024 event. Apple recently announced Apple Intelligence, Copilot alternative, Apple Swift Code Assist, Siri Updates, AI updates & ChatGPT Integration. I'll be talking about it all in this video. Key Takeaways: 📱 Apple Intelligence: Discover how Apple has integrated new artificial intelligence features into iPhones, ...
Serverless is a myth (Ft. Vercel & Cloudflare)
zhlédnutí 1,4KPřed 14 dny
In this video, I'll be talking about why serverless is a myth made by people at AWS, Vercel & Cloudflare who wants to take all your money. I'll be discussing the recent events that happened with a Cloudflare user where they were asked to pay $120K, whereas I'll also be talking about the recent $96K Vercel bill charged to a person. I'll be telling you that how you can reduce your Server costs by...
LightningAI + InvokeAI: STOP PAYING for Midjourney with this FREE, LOCAL & OPENSOURCE Alternative
zhlédnutí 4,8KPřed 14 dny
LightningAI InvokeAI: STOP PAYING for Midjourney with this FREE, LOCAL & OPENSOURCE Alternative
Qwen-2 + ContinueDev + ShellGPT : This Coding Copilot is LOCAL, FREE & Amazing! (works without GPU)
zhlédnutí 6KPřed 14 dny
Qwen-2 ContinueDev ShellGPT : This Coding Copilot is LOCAL, FREE & Amazing! (works without GPU)
This SECRET Google AI Coding Tool is FREE & Amazing! (Generate Code, Fix Bugs & Optimize Code)
zhlédnutí 10KPřed 14 dny
This SECRET Google AI Coding Tool is FREE & Amazing! (Generate Code, Fix Bugs & Optimize Code)
Qwen-2 : The BEST Opensource LLM is here & It's Amazing! (Beats Llama-3, GPT-4O, Claude)
zhlédnutí 12KPřed 14 dny
Qwen-2 : The BEST Opensource LLM is here & It's Amazing! (Beats Llama-3, GPT-4O, Claude)
PHP is perfect, unlike React
zhlédnutí 2,7KPřed 14 dny
PHP is perfect, unlike React
TLBrowse: Opensource Text-to-Frontend AI with Multiple Page Generation (OpenUI & v0 Alternative)
zhlédnutí 2,3KPřed 14 dny
TLBrowse: Opensource Text-to-Frontend AI with Multiple Page Generation (OpenUI & v0 Alternative)
They Stole & Copied work from Other's Code? (Opensource Drama)
zhlédnutí 2,5KPřed 21 dnem
They Stole & Copied work from Other's Code? (Opensource Drama)
Aider + CodeQwen : This AI Pair Programmer is BETTER than Github's Copilot (works w/ Ollama, OpenAI)
zhlédnutí 6KPřed 21 dnem
Aider CodeQwen : This AI Pair Programmer is BETTER than Github's Copilot (works w/ Ollama, OpenAI)
RapidPages: Opensource Text-to-Frontend AI with 100% LOCAL Setup (OpenUI & v0 Alternative)
zhlédnutí 6KPřed 21 dnem
RapidPages: Opensource Text-to-Frontend AI with 100% LOCAL Setup (OpenUI & v0 Alternative)
Twinny + Codestral (22B) : STOP PAYING for Github Copilot with this NEW & BETTER LOCAL Alternative
zhlédnutí 5KPřed 21 dnem
Twinny Codestral (22B) : STOP PAYING for Github Copilot with this NEW & BETTER LOCAL Alternative
Farfalle + Phi-3 + Tavily: STOP PAYING for PERPLEXITY with this NEW, LOCAL & OPENSOURCE Alternative
zhlédnutí 4,7KPřed 21 dnem
Farfalle Phi-3 Tavily: STOP PAYING for PERPLEXITY with this NEW, LOCAL & OPENSOURCE Alternative
Mistral's Codestral (22B): The BEST Opensource CODING LLM is here! (Beats Llama 3, GPT-4O & Claude)
zhlédnutí 5KPřed 21 dnem
Mistral's Codestral (22B): The BEST Opensource CODING LLM is here! (Beats Llama 3, GPT-4O & Claude)
RAGapp: This NEW & EASY way to CHAT with PDFs is better than ChatGPT (works w/ Ollama,OpenAI,Gemini)
zhlédnutí 3,8KPřed 21 dnem
RAGapp: This NEW & EASY way to CHAT with PDFs is better than ChatGPT (works w/ Ollama,OpenAI,Gemini)
Fabric: This OPENSOURCE AI Framework can AUTOMATE YOUR LIFE & ANY TASK (Setup with Ollama & Groq)
zhlédnutí 13KPřed 28 dny
Fabric: This OPENSOURCE AI Framework can AUTOMATE YOUR LIFE & ANY TASK (Setup with Ollama & Groq)
ShellGPT + Phi-3 : OPENSOURCE & LOCAL AI Copilot for your TERMINAL (Github Copilot CLI Alternative)
zhlédnutí 4,2KPřed 28 dny
ShellGPT Phi-3 : OPENSOURCE & LOCAL AI Copilot for your TERMINAL (Github Copilot CLI Alternative)

Komentáře

  • @Msyo_Jaber
    @Msyo_Jaber Před 2 hodinami

    this is so usofel i larn alot but a ves issue

  • @satjeet
    @satjeet Před 2 hodinami

    Muchas gracias crack.

  • @MuhanadAbulHusn
    @MuhanadAbulHusn Před 3 hodinami

    Can you give a hint about the minimum hardware resource required for running the models you've done locally?

  • @josedelarocha2455
    @josedelarocha2455 Před 4 hodinami

    Man, what is your setup to be able to run something like this?

  • @EladBarness
    @EladBarness Před 8 hodinami

    You are the king of AI code king

  • @jaradaty88
    @jaradaty88 Před 9 hodinami

    That is cool

  • @KS-tj6fc
    @KS-tj6fc Před 10 hodinami

    7:40 can you show us the total Input/Output Tokens used for the various LLM configurations (in all videos going forward, like a token counter on the bottom corner of the screen/Visual Studio). Example 3.5 Sonnet as Orchestrator, (Free) Deepseek CoderV2, Gemini Flash for final? And how many tokens were used by Gemini Flash in All Roles, 3.5 Sonnet in All Roles. What’s the token savings when the main work is done by local (free) model, or cheaper Gemini Flash. Also - how about Deepseek Coder-V2 API, costs are only (In $0.14/ Out $0.28) per million tokens. Is Sonnet Using 10k tokens, Deepseek 150k and thus $0.18 sonnet and $0.04 Deepseek once combined?? Thank you for all your help and videos!!!

  • @bobgeorgeff
    @bobgeorgeff Před 10 hodinami

    When you test the generated code, what platform)s) are you using to compile/run it?

    • @bobgeorgeff
      @bobgeorgeff Před 9 hodinami

      I know Claude has a “preview” box, but it looked like you’re using something else maybe?

  • @jackflash6377
    @jackflash6377 Před 10 hodinami

    Thanks!

  • @mugenmugen5237
    @mugenmugen5237 Před 11 hodinami

    Can it all install in different directory?

  • @world-78913
    @world-78913 Před 12 hodinami

    Bro what,s on you right side of visual studio code ?

    • @AICodeKing
      @AICodeKing Před 12 hodinami

      Actually, I use lightning AI for the videos. There you get multiple options like Terminal, VSCode, Jupyter Interface & Stuff like that.

    • @DavidSeguraIA
      @DavidSeguraIA Před 4 hodinami

      @@AICodeKing thanks,with the free tier of lighting so is enough or is the pro tier necessary? By the way which tier you use in this tutorial?

  • @tomjia3072
    @tomjia3072 Před 12 hodinami

    Thanks!❤

  • @aamironline
    @aamironline Před 12 hodinami

    Can it read the existing project code improve it?

  • @AseemChishti
    @AseemChishti Před 12 hodinami

  • @jocksizer1123
    @jocksizer1123 Před 12 hodinami

    I have an RTX 4070 Super, I am pretty sure the 72B is impossible to use, will the 7B be sufficient?

    • @AICodeKing
      @AICodeKing Před 12 hodinami

      I have tried it with that and It was fine as well. Also, the best part is that you can try multiple LLMs to see what fits you the best.

    • @jocksizer1123
      @jocksizer1123 Před 12 hodinami

      @@AICodeKing Thanks for the response! I'll do it then :) btw, loved much more this Mastro than the one with Sonnet 3.5. The homepage layout fits much better! Thanks for the constant updates on LLM's.

    • @FawziBreidi
      @FawziBreidi Před 9 hodinami

      i wonder why vram is the only solution? for example i have 128GB of ram, cant ollama use system RAM? if someone would like to explain to me how these models consume system resources

  • @Beatmakerniko
    @Beatmakerniko Před 13 hodinami

    Its pretty cool!

  • @dasdassdarrrr
    @dasdassdarrrr Před 13 hodinami

    Can you upload your existing repo into it and generate new stuff with it?

  • @ayasugihada
    @ayasugihada Před 13 hodinami

    Thanks! Which one is the best with their highest paid tier? Or are these comparable when you pay for them?

    • @AICodeKing
      @AICodeKing Před 13 hodinami

      LightningAI is the best in my opinion

    • @ayasugihada
      @ayasugihada Před 13 hodinami

      @@AICodeKing thx a ton!

  • @silentspy6980
    @silentspy6980 Před 13 hodinami

    um could you please tell me like how much better is claude sonnet 3.5 than deepseek coder v2?Cuz I wanna make a real good txt to code ai .But the thing is I dont wanna pay and I have reverse engineered the deepseek coder v2 website giving me completely free and unlimited usage of deepseek coder v2 for free as an api.But it is almost impossible for the sonnet also it allows only a limited prompts so yeah if the difference is of 10-15 % then i will go with deepseek.edit:One nother question so like for the orchestrator can i take a ai that is good in chat but not in code or does it have to be good in code?

    • @AICodeKing
      @AICodeKing Před 13 hodinami

      I would say Sonnet is 30% better than DeepSeek

  • @legendarystuff6971
    @legendarystuff6971 Před 13 hodinami

    I think I will go with sonnet for orchestration and refining and deepseek coder for the agentic taskss

  • @Techonsapevole
    @Techonsapevole Před 14 hodinami

    Fantastic, what about the incremental changes via chat ? openui does it

    • @AICodeKing
      @AICodeKing Před 14 hodinami

      This doesn't do that but it can create much more than just frontend and in any programming language.

    • @jackflash6377
      @jackflash6377 Před 10 hodinami

      You could feed the file you want to change to ChatGPT-4o or Sonnet and have them refine it. Both make good UI generators.. with feedback.

  • @user-wr4yl7tx3w
    @user-wr4yl7tx3w Před 14 hodinami

    but can you see the code? is it using langchain?

  • @jackflash6377
    @jackflash6377 Před 15 hodinami

    So far I've used it to generate two small apps. Web based inventory scanner to use on a tablet as a portable inventory scanning tool. Peptide dose calculator Total cost $0.35 VS Using straight up Opus to design a similar inventory scanner at $20.16 (this one used a backend and connected to the database, the other just made a CSV file on the backend) Nice!

    • @jasonliu6321
      @jasonliu6321 Před 4 hodinami

      what are your prompts to generate the inventory scanner? is it just one simple text or complicated description file?

  • @chieeyeoh6204
    @chieeyeoh6204 Před 17 hodinami

    For real? GitHub Copilot still use GPT-3?

  • @matizbrave
    @matizbrave Před 19 hodinami

    How does it compare to Claude 3.5?

  • @diakorudd7268
    @diakorudd7268 Před 22 hodinami

    I try to use lightningAI like you are doing in this video but its not allowing me to create the ~/.config/shell_gpt/.sgptrc . How did you work around this ? Thanks for uploading your gemstones of videos.

    • @AICodeKing
      @AICodeKing Před 22 hodinami

      You'll need to first run the SGPT command then it will be automatically created.

    • @diakorudd7268
      @diakorudd7268 Před 22 hodinami

      PermissionError: [Errno 13] Permission denied: '/teamspace/studios/this_studio/.config/shell_gpt/.sgptrc'

    • @AICodeKing
      @AICodeKing Před 20 hodinami

      Try running it with Sudo or run "sudo chmod 777 /teamspace/studios/this_studio/.config/shell_gpt/.sgptrc"

    • @diakorudd7268
      @diakorudd7268 Před 20 hodinami

      @@AICodeKing I got it to work in github codespaces but its still not working in lightning because its not allowing me to change permission of .config/ folder or any subdirectory .config/*

  • @jdholbrook33
    @jdholbrook33 Před 23 hodinami

    Any idea what the "Do you want to add a text file?" does? Text file to describe the project or text file to include data etc.. ?? First test was a success. Thank you !!!

    • @AICodeKing
      @AICodeKing Před 22 hodinami

      I believe it's for a bigger prompt if you want to give or for a context.

  • @yokowasis
    @yokowasis Před 23 hodinami

    You must apply for studiolab, and lightning ai is not available for some country, paperspace free tier machine most of the time is not available. In these cases, they are useless and unusable. Nice find with huggingface and codespaces.

  • @veroxsity2336
    @veroxsity2336 Před dnem

    You pay for copilot?

  • @MuhanadAbulHusn
    @MuhanadAbulHusn Před dnem

    can you show us an example how to connect these front ends to the back end ifthe last is in Python?

  • @woofwoofification
    @woofwoofification Před dnem

    Is there a way to make it know your local code?

    • @AICodeKing
      @AICodeKing Před 22 hodinami

      Yes you can add your context file to it

  • @geomorillo
    @geomorillo Před dnem

    So am i gonna be unenployed soon?😢

    • @AICodeKing
      @AICodeKing Před dnem

      Start building AI so AI can't replace you. (Big Brain 🧠 Time)

  • @Kashif-kk7qm
    @Kashif-kk7qm Před dnem

    Brother tell us how to deploy and run llama 3 or other open source models on Amazon sagemaker studio lab, kaggle or colab please make detailed video on these topics 😊😊

  • @jimbig3997
    @jimbig3997 Před dnem

    Looking for a solution that does not use Microsoft retardware Visual Studio.

  • @johannesdeboeck
    @johannesdeboeck Před dnem

    You are the best 🤩

  • @leonkohli
    @leonkohli Před dnem

    I have built a Chrome Extension that enabled Preview of HTML directly in the ChatGPT interface, full open source and available in Chrome store "ChatGPT Web Preview"

  • @zheng2hao
    @zheng2hao Před dnem

    dayum, you edit and upload fast! Efficient! super stoked everyday since you almost upload everyday. Lots of love!

  • @jackflash6377
    @jackflash6377 Před dnem

    Interesting test, showing how the local model was not able to provide the logic for the code. Pointing out that Ollama is using the Q4 version. The Artifacts feature is very helpful. I hope the developer fleshes it out.

  • @chbaha5834
    @chbaha5834 Před dnem

    Does it work with local models like qwen2 or deepseekcoderv2 ? If so is it actually the best llm agent framework?

  • @BadreddineMoon
    @BadreddineMoon Před dnem

    What are your hardware specifications?

    • @tofani-pintudo
      @tofani-pintudo Před dnem

      DeepSeek coder v2 is working fine on my MBA 16 GB

    • @eternalkino34
      @eternalkino34 Před dnem

      @@tofani-pintudo dumb question but why do you guys need LLM's to be locally installed other than working offline or training models ??

  • @sievo666
    @sievo666 Před dnem

    The way to change any app from an API to local endpoint is the same no? So anything with API can be changed to local?

  • @rcingfever3882
    @rcingfever3882 Před dnem

    Your way of talking is awesome sarcastic humour

  • @ATHEEK29
    @ATHEEK29 Před dnem

    Good

  • @Tofu3435
    @Tofu3435 Před dnem

    Can i create simple games to my phone without ads/micro translations? Then worth it.

  • @thedeadlypretzel
    @thedeadlypretzel Před dnem

    Thanks for the video! Though as a developer with 15+ years experience that really, really loves AI, I have to say projects like this suck tremendously. You have very little control over the output, and making all the changes you want to make will definitely feel a lot more like fighting the system rather than using it. Projects like this are only good for youtube and for going "wow look at what we can do with single prompt" But imagine if it has to be a production-ready application where 5 managers, a product owner, and a test-audience all want to have something to say about what it should look like, what it should do, ... Even if it's just for yourself, the tech is not there yet and you'd be way better off having a symbiotic relationship with AI tools rather than trying to force them to do things they are not made for and have them completely take over work only to deliver bad code that cost a lot of money (cause face it you will have to end up using the best/most expensive model if you want anything more than playthings) I highly recommend taking approaches like in the "Atomic Agents" library: github.com/KennyVaneetvelde/atomic_agents

  • @AnthonyG-p6k
    @AnthonyG-p6k Před dnem

    Give your contact email for Sponsorships.

  • @AnthonyG-p6k
    @AnthonyG-p6k Před dnem

    Give your contact email for Sponsorships.

  • @tobeyforsman
    @tobeyforsman Před dnem

    Pretty cool

  • @mhbakus
    @mhbakus Před dnem

    pretty cool video. well done king

  • @siddharthduggal
    @siddharthduggal Před dnem

    Thanks!