alexei_rudak

Thanks! But I'm still not in my dream, may be next year will be able to create technology that can do that with desired level of quality ))

I would love to have my own service and technology to localise videos by using AI. All startups in that niche are growing so fast.

I've trained LLM to make conversion from American English to British English and vise versa. To do that I've used 10k sentences for fine-tuning.

I mean the case when tiny models can outperform LLM on certain tasks. For example storytelling, and only for Harry Potter world. Something very niche but with maximum quality that can't do other tasks. Just want to see an example of that tiny model.

Did you try to optimise your model for specific tale, game characters etc ?

Tried your service. Once I sent my question and got the answer it's not possible to enter another request in the search field. Possible a bug ?

The more and more generated content by AI (audio, images, text, files etc) will turn Internet into trash.

The community of dancers once I decided to learn Cuban Salsa. It was the best choice for me to feel happy.

This is a period of uncertainty in the world, so buyers are waiting for lower prices

Local translation is a good choice in case of privacy, but small language models can't offer a good translation quality like Chrome. Brave and Vivaldi browsers use on-premise translation by Lingvanex which helps to avoid transmitting your data to Google or other third-parties

Just separate all critics in 2 parts:

1) Professionals in your sphere: Take as much critics from professionals in your sphere as you can. Sometimes you need to even pay for this. Analyse and go forward. The more mistakes you will make the faster you will reach your goal. Act it as a game.

2) All others: Just tell them magic words: "This is only your opinion, Thanks!" and do nothing.

Be happy )))

Wrap it as iOS or Android app with ads and send to Appstores. Even with integrated ads like Admob you can easily cover your expenses

As I know it's impossible for current large language models to return "real-time" data, because you need to retrain it after every data update. And this will take time.

I tried several of open LM to test what they can. The performance is very poor on PC with GPU and quality is far away to use them in commercial tasks. But to play for fun and chat like a friend "Hello, what do you think about cats? " can be ok.