Skip Navigation

Posts
3
Comments
14
Joined
3 yr. ago

  • . Gemma and Qwen I run locally on a strix halo framework desktop

    So, CPU only?

  • nanogpt

    Do you know how nanogpt compares with openrouter? Why did you pick nanogpt?

  • How do you get your LLM credits? Or do you run Gemma and Qwen locally? With which hardware?

  • You can use opencode with a lot of different setups though, you don't need to go for their subscription model.

  • Thank you!

  • What hardware do you use? How fast is it?

  • Programming @programming.dev

    Ask Lemmy: What do you currently use for AI coding?

  • That's true, but there are also massive economies of scale when you can afford the big Nvidia gpus and share them among many people.

  • I agree. I use openrouter myself.

  • In general I agree with you, but llms are the one exception where it's not practical and not cost effective to run them locally. If you want to use them, the better option is by far to pay someone for the service.

  • United States | News & Politics @lemmy.ml

    4 dead in 30-vehicle pileup in Colorado as powerful winds slam Plains, fueling multiple wildfires

    edition.cnn.com /2026/02/17/weather/fire-oklahoma-texas-kansas-colorado-climate
  • United States | News & Politics @lemmy.ml

    The US slips to its lowest-ever rank in a global corruption index

    edition.cnn.com /2026/02/10/business/corruption-index-transparency-international-united-states-intl
  • When you're a government, you need a little more process to ensure things are done well (moderation, security, ...). Even something simple like that could take valuable time from quite a few people.

  • Sad but unfortunately fairly justified. Hard to justify spending public money on 3,500 users.

  • Rust, haskell, python, c++ are all interesting choices. I would argue that c# is too close to what you already know to be interesting.

    If I were you though, I'd pick a project first, then decide what language makes sense for it.

  • I don't understand why they don't use a second model to detect falsehoods instead of trying to fix it in the original LLM?