Live data from Hacker News

Viewing profile — jonas_scholz

jonas_scholz

HN member
Joined
Wed, Oct 28, 2020, 10:04 PM UTC
HN karma
114
Public activity
44 items

About jonas_scholz

No profile information was provided.

Recent public activity

  1. comment
    Comment #49048449

    They wont, they are very public about never subsidising any products. I doubt they change that after 29 years now.

  2. comment
    Comment #49040695

    also slightly disrespectful to think that this was a single prompt, but ok:D

  3. comment
    Comment #49039105

    yeah, but why would LLM inference now triple the price of the other products? Or am I misunderstanding what you're saying?

  4. comment
    Comment #49037013

    "no reason" like hardware prices going through the roof?

  5. comment
    Comment #49034799

    Why do you think this would be madness? It seems like, at least in the EU, there is barely competition for the big open-weight models?

  6. comment
    Comment #49034702

    fine, i agree that this doesnt sound like me. But the content is correct and not a hallucination!

  7. comment
    Comment #49034600

    I mostly use Hetzner baremetal servers and not cloud, but the support there is in my experience very competent, but also VERY german and direct. I can imagine if youre neither germ…

  8. comment
    Comment #49034527

    what is the hallucination here? it is fast, free and fun to try. And I genuinely think that the hardware decision (if they get bigger gpus) decides if this will be a banger product…

  9. comment
    Comment #49034210

    yea, but no prompt caching right? This makes it unusable for my usecase at least, the cost would be insane

  10. comment
    Comment #49034150

    I really hope they dont stop at the small models though! The bigger ones that dont fit on a single GPU are more interesting I think

  11. comment
    Comment #49034102

    agree. I have a usecase for a bigger open-weight model hosted by an EU company and the selection isnt really great, hard to make the regulatory gods (and the devs) happy at the sam…

  12. comment
    Comment #49033870

    My writing wasnt clear here I think, without the option it defaults to reasoning enabled. With "without it" I meant without enable_thinking=False!

  13. comment
    Comment #49033584

    Interesting, didn’t know about them! Weird model selection though, no glm or deepseek?

  14. story
  15. story
  16. comment
    Comment #46857549

    we love and support netbird at sliplane https://docs.sliplane.io/private-networking/netbird

  17. story
  18. comment
    Comment #45939919

    Thank you for mentioning Sliplane! Really cool project.

  19. story
  20. comment
    Comment #43280424

    afaik no firecracker support with virt-manager. There's firectl to make it a bit easier but the tooling is generally still pretty rough

  21. story
  22. comment
    Comment #42711453

    Yes, we're on Hetzner! The availability is actually insane. Thank you :)

  23. comment
    Comment #42711443

    Thats cool! Id like to check that out if you want to share! jonas@sliplane.io or you can find me on Twitter/X (JonasScholz19) :)

  24. comment
    Comment #42699262

    BTW, this is also kinda how Sliplane started. We both are coming from a freelancing background and had built similar things for clients before

  25. comment
    Comment #42699230

    Yes! And its not like we don't care about that or don't want to follow all the rules, it's just really hard. Especially when you're not funded and a tiny team.