danielEM

If you're a software developer and using coding agents "all the time" for your work please share here your bills and APIs you're working with. I was easily able to burn $1 a minute with deepinfra. But I have just tried…

Can't find "apple to apple" comparison on performance on QWQ 32b (4bit), can anyone help me with decision on which solution to pick? From what I dig so far it looks like dual Arc A770 is supported by llama.cpp. And saw…

Is AI gonna take over these jobs? What tools to use? Where to head first steps? Any volunteering opportunities in that area?

For what purposes you use llama.cpp? What tools do you use with llama.cpp? Is there anything you recommend to avoid when it comes to llama.cpp? Want to collect your best practices/experiences and advice around…

Personally having an issue like this one: [ 6488.577727] [drm:amdgpu_job_timedout [amdgpu]] ERROR ring gfx_0.0.0 timeout, signaled seq=1715593, emitted seq=1715595 [ 6488.577881] [drm:amdgpu_job_timedout [amdgpu]] ERROR…

And if so what you're running on it and what is its performance? Don't want to throw multiple kUSD just for running llama and stable diffusion at reasonable speeds and I'm wondering how much reasonable in this field is…

What is your programming language and it's status? Can you share a link to its code?

What are your best practices to scale a team when it comes to working with AWS infrastructure? Eg. what do you do when you need 2-3 devs to develop different features for same lambda?

Has anyone managed to run llama 2 on Vulkan? If so, what is your soft stack?

Was wondering if I was to buy cheapest hardware (eg PC) to run for personal use at reasonable speed llama 2 70b what would that hardware be? Any experience or recommendations?

What does LLVM have that can not be achieved 1 to 1 in C? And what does C have that can not be reproduced 1 to 1 in LLVM? And when I say C I mean tcc, sdcc, gcc, clang and other C compilers. It feels to me like C should…

Not asking for myself, but for all those who are looking for these type of positions. Feel free to throw any open positions - even non paid ones for free and open source projects.

There is a lot solution about code generation by neural networks, but I don't see any attempts on recreating code based on machine code/assembler. Use cases for it: 1. Transpilation - you have a project in one "old"…

For me glasses works, they appear as single display 1920x1080 but that is about it. No access to sensors nor stereo mode available. Would be happy even if was able to move 2D virtual screen with my head movement. But…

All emotions aside, want pros and cons opinion from people who actually did something in below programming languages and have 2+ years of dev experience in general https://ec-lang.org/ https://vlang.io/…

Looking for javascript/typescript components library that doesn't rely on any framework. And best if it would support resizable and moveable "windows"

I'm curious what was the state of an art in robotics area in 60s in different countries, feel free to post links to videos and pictures. Here is my country - Poland: https://www.youtube.com/watch?v=NjrYk546uBA

That topic is bugging me for a little while. Anyone who follows me (probably 0 people ;-) ) knows already that I'm not a fan of cryptocurrencies. And I'm not gonna dive into that here. Instead I'll try to solve one of…

Recently working on my own framework https://github.com/DanielMazurkiewicz/hussar. (this is at the stage of "working concept" of "work in progress" and when there will come a time, I'll do "Show HN" instead of "Ask HN"…