Видео

I only use Cursor and Claude for coding and Claude is definitely better than ChatGPT and Qwen in my opinion. I don't know your computer may run it or not but you can basically install the LM Studio and try.

@ Why do you prefer Claude over GPT for programming? Are there certain use cases/quality that you’ve seen you like better? Have you tried o1 mini?

i am not ai dev so i am not sure how it work sorry for dumb question

@@MrFluke039 If you have a powerful machine and if you don’t want to pay for a paid service then it’s why you want to run a local LLM. Reason why you use Ngrok is because Cursor cannot access to your local LLMs. It does everything on their server so the LLM model should be on a server too.

@@raadkasem Thank you. I will 🚀

@@raadkasem I’d like to try it if I find an easy way to install it

LM Studio recently added support for MLX, so I believe the demo in the video is already using MLX.

@@johnbean3429 Sure it does, but if you noticed the model he selected was GGUF in a purple badge next to model’s title not MLX with the grey badge At 0:02

@@johnbean3429 where is there a freaking video of it then on youtube can't find like pls.

Cursor does everything on their server so it can’t connect to localhost.

I only tried for JS and I can’t say it’s better but it’s close to Claude and ChatGPT quality. Also keep in mind the model may respond better on different programming languages.

@@ozgrozer Thanks for your reply :)

There are some open source alternatives but I think Ngrok is the most popular one

No it's 36GB. I sped up the video on model response because it was too boring to watch. But the speed is mostly 12 tok/sec.

@@ozgrozer I have 24gb m4 pro, I don't think I have enough memory to run it as LM studio was giving me errors

@@daburritoda2255 You could try Ollama too. But even if you could run, it would be very slow to respond I guess.

@@ozgrozer yeah i did, no luck 🙁, have you tried running the MLX version? if so how does it differ from the GGUF quantisation

​@@daburritoda2255 I only tried the GGUF version and the Mac was on fire after a couple of minutes chat with Qwen. I think you even need a more powerful machine.

@@molmock Thank you. It’s Screen Studio.

@ozgrozer thank you !

What are your Screenstudio export settings? Looks great!

⁠@@Businessology.I don’t do any custom settings. Just choosing this background image.

Yeah it’s very easy. You need Ollama installed in your machine. Then a model like Llama3, Gemma2 for file renaming and Llava for image renaming. Then you just run ‘npx ai-renamer /path’.

You can see more on the links in the description. GitHub github.com/ozgrozer/ai-renamer X Post x.com/ozgrozer/status/1810033026270675195

You don’t get the point. It doesn’t matter it would take same amount of time as manually adding videos. It’s not your time you’re spending here. It’s computer’s time. On manual adding you have to be on the computer and spend some time to add all the videos. It’s a super boring thing btw. On the other hand if you let this script to do the job then you don’t have to be on the computer. While it’s working on it you can go read some books about concept of time.

@@ozgrozer If a channel has thousands of videos, it takes ages for them to load. The script didn't even work, always displaying "adding 0 videos in 0 seconds".