‹ BackHN Continuity

Thread

Jev in 25 Lines of Python

691 points · 212 comments · bashbjorn

  1. dhsysusbsjsi · · focus · HN ↗
    Whilst I do like reading these things for technical know how, I can sympathise with the creator of jev who now presumably has to apply an order of magnitude effort to explain why the 100 smaller things done better than this add up to a much better product.
    1. ramon156 · · focus · HN ↗
      IT's the infamous "OneDrive in 10 lines of code (SFTP)"

      While technically correct, it's not the same thing

      1. pjerem · · focus · HN ↗
        It's not the same thing but it have advantages Jev don't have like ... being local.
        1. estetlinus · · focus · HN ↗
          From what I’ve learned about Jev I feel it’s just a very successful marketing campaign to developers not fully understanding data science (and deep learning). It’s nothing new, been around since 2022? Being local is an extreme advantage lol.
          1. baobabKoodaa · · focus · HN ↗
            Fast and accurate general purpose classifiers DID NOT EXIST before Jev. You could either use an LLM to get a slow and accurate general purpose classifier, or you could use a smaller model to get a fast and inaccurate general purpose classifier, or you could fine tune your own model that would be both fast and accurate, but it wouldn't be general purpose.
            1. hbrn · · focus · HN ↗
              But we still don't have a fast and accurate classifier.

              All we have is a company that claims to have created one, with no proof.

              1. baobabKoodaa · · focus · HN ↗
                I've seen enough proof to convince myself, but unfortunately I don't have enough to convince you. Maybe others will publish proper evals.
      2. baobabKoodaa · · focus · HN ↗
        Except in this case it's not technically correct. Jev's claim is that it's frontier intelligence and these guys are pretending that a 8-bit quantized 0.6B param Qwen model is that. There's no universe in which that claim is technically correct.
        1. hartator · · focus · HN ↗
          Isn’t Jev built on top of Qwen?
          1. baobabKoodaa · · focus · HN ↗
            Is Jev built on top of 8-bit quantized 0.6B param Qwen model? No.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.