Video

this is so usofel i larn alot but a ves issue

Muchas gracias crack.

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

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

You are the king of AI code king

That is cool

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!!!

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

Thanks!

Can it all install in different directory?

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

Thanks!❤

Can it read the existing project code improve it?

❤

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

Its pretty cool!

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

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

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?

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

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

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

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!

For real? GitHub Copilot still use GPT-3?

How does it compare to Claude 3.5?

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.

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 !!!

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.

You pay for copilot?

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

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

So am i gonna be unenployed soon?😢

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 😊😊

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

You are the best 🤩

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"

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

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.

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

What are your hardware specifications?

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?

Your way of talking is awesome sarcastic humour

Good

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

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

Give your contact email for Sponsorships.

Give your contact email for Sponsorships.

Pretty cool

pretty cool video. well done king

Thanks!