betimsl

The problem with these is the tool calling. From my experiments qwen agent almost always fails with tool calling and porting the correct config is quite tedious.

Rio3.5 with Qwen compatible tool calling, we need that :)

what a legend!

PocketBase is awesome and this thing looks awesome.

One question, I could not understand if a mail provider is needed or it handles on its own?

Could you please make the book into a PDF?

Who wrote the algorithm?

More important that if it is a good programmer or not, is to be able to spot if the guy can get the job DONE.

The story is that Ken and Rob were at a diner when Ken gave structure to it and wrote the initial encode/decode functions on napkins. UTF-8 is so simple yet it required a complex mind to do it.

Right, but Intel is in no position to do that. So, they could play and put 32GB VRAM and also, why not produce one with 64GB just for kicks?

Dream phone: Underclocked Samsung25 internals, iPhone SE design/dimensions, at least 90hz OLED panel, 1 back decent camera, 1 front too. 3A battery. Preferably an extenal SD card slot.

Awesome.

I think you could easily give the UI a refresh, modernize it a bit :)

It's simply not Apple's responsibility. Person's data, their responsibility. Any other way and people lose trust in Apple which BTW they protect it by any means. Trust.

Instead of wanting something impossible, accept the reality.

Apple’s encryption, is designed with end-to-end encryption for many types of data.

Some facts:

    Only the user's devices hold the keys to decrypt the data.

    Apple cannot decrypt it, even if served a subpoena.

Apple chose privacy over convenience. Sue all you want, you're going to lose.

Uhoh! -- The virus just spread a litl more!

Check out NVIDIAs latest releases. Paying for tokens is going to be a history in about 6 months. You run the model on your laptop.

Maybe you're right about the confusion...but given the velocity, that's going to be fixed also.

All the knowledge about the field of programming is digitized, one could argue that having a model that digested all that information in a right way, is better than separate.

Just a thought. I don't care all that much.

They probably screw the patients too.

Why separate? It's not like there's limited capacity...you can have an assistant knowing all the languages at once.

You have a typo in the snippet on README.md: SchlüsselWert should be Schlüsselwert.

> [...] This is to the point where is starts to become hard for you to work without one.

Why would one work without one?

> Why?

Huge interest in the field. Schools unable to teach the craft properly.

Glad that I'm not the only one doing just that.

Any chance open sourcing it? :)

Material tolerances.

Running a 7b coder in laptops with 4060 is possible and with very good results. Orra looks like a very good tool to be integrated with any IDE. Take a look at this: https://github.com/huggingface/llm.nvim -- it has a backend option. Ollama exposes a REST API, I think you guys should support it :)

I mean, local LLM, for example: can it be run with llamafile instead of cloud AI?

I don't see local backend in documentation. Is it possible?

Reads nicely from right to left.

how much is the cost of a kW in Germany?

Equivalent to a beginner betting $500 on red. Let's see what happens.

It just makes everything perfect.