OpenJev

80 points | by ilreb an hour ago

31 comments

  • kul_ 12 minutes ago

    Is it only me or do others also find LLM generated websites so off-putting?

      alex_suzuki 4 minutes ago

      Same. I can’t really put my finger on what exactly is turning me off though. I mean, apart from the obvious AI-generated text.

      cgio 2 minutes ago

      Maybe I am conditioned, but I found it nice and clean.

      tjoff 5 minutes ago

      This one is so much better than the vast majority of sites though?

      Clear and to the point. Not even a cookie popup (which ni user respectable site needs, so super low bar to clear).

      If you meant the text then I agree.

      kjeksfjes 8 minutes ago

      As a designer; only slightly. I'm not there to be blown away by awesome design.

      bloody_bocker 8 minutes ago

      For me it's a bit like with some of the LLM prose - uncanny valley territory.

      rtpg 5 minutes ago

      People rushing to throw a thing out into the world, rushing so much that they don't even bother to use it or look at it themselves.

      The same people who are likely seeing tens of the same sort of pages and immediately closing them because "who cares".

      I mean I guess I'm looking at this too. But at this point the most interesting projects in the world to me are ones with bad CSS.

      olexsmir 10 minutes ago

      you're not alone

  • wuhhh 6 minutes ago

    I don't understand how this is different from oai "structured output" (and whatever the similar paradigm was on Sonnet ~3.7 back then) which everyone moved on from. On their gh they say:

    "Jev is TypeSafe's closed service for runtime-defined semantic decisions. This project reproduces that interface pattern with open models; it does not reproduce Jev's undisclosed model or training"

    As someone else pointed out it isn't actually Jev... can someone enlighten me

  • algoth1 a few seconds ago

    Isn't Jev a trademark?

  • lucfranken an hour ago

    Jev is such a different approach where you have to be specific about what you want and which options are open. Really interesting how those things evolve in usable features for people.

    Also with this example the speed of new launches based on a launch is just incredible.

      chvid 41 minutes ago

      "... such a different approach where you have to be specific about what you want and which options are open" --- back to where we started ...

        lucfranken 34 minutes ago

        Not sure on that, maybe the options to choose from will be generated and curated. Same as we do with tagging datasets for images. Might be wildly successful for real world decisions.

  • tomaytotomato 17 minutes ago

    Unfortunately huggingface.co is blocked by my company's firewall and VPN so it breaks when downloading a model.

    Are there any huggingface mirrors out there?

  • tecleandor 32 minutes ago

    I'm confused... This has no relation with the Jev team, isn't it?

    It's trying to "emulate" Jev behavior using a regular small LLM model (Qwen3 0.6B or MiniCPM5 2B). And with the smallest model it takes like between half to two seconds to run in my M2 Max, so it's not super fast.

    I mean, it's faster than asking to a regular LLM, but I think that's not proper to have Jev on the name (also legally...)

    Edit: no shade, and I'll give it a try for some ideas. I'd also like to have an open weights Jev but I think the naming is misguiding. I also have to try Jev that, BTW, got access pretty quickly, less than a day I think...

      CharlieDigital 15 minutes ago

      OP's point here is that the overall approach of restricting output token space and using parallel prompts to produce concurrent results and taking the most relevant ones isn't something novel to Jev (not saying there's nothing novel, but a facsimile can be created at the application layer using any small, fast model)

        Foobar8568 a few seconds ago

        I still don't get the point of jev....it's basically an optimized models/runner on really short context and output?

  • phoghed 34 minutes ago

    > Give it a real choice

    As opposed to a fake choice?

      hbcdbff 2 minutes ago

      Claude insists on injecting the word real or actual everywhere.

      I kinda wonder if being trained on other English dialects, particularly Indian English, causes this

      philipp-gayret 8 minutes ago

      Anthropic's Claude fingerprinting technology at work; randomly inject "real" everywhere. If it was Codex you would have seen load-bearing choice.

  • jasurme 4 minutes ago

    did you use chatgpt to create this?

  • hbcdbff a minute ago

    Impossible to tell if this is slop or not

  • neilellis 28 minutes ago

    Correct me if I'm wrong but Jev itself works pretty much the same as encoder only models.

  • camillomiller 13 minutes ago

    I tried this:

    "Customer wants to lear how to better talk in a company situation, and bring across their argument effectively"

    Than had it choose what training would be fitting for this user: - Communication and Feedback - Leadership for Begninners - Soft Skills and Emotional Awareness

    It picked always the third with an 80% confidence, while the answer should have been 1.

      arcwhite 9 minutes ago

      You sure the answer should have been 1? As a human I'd say I don't have enough information to answer this confidently, but "argument effectively" strongly suggests soft skills to me

  • ares623 21 minutes ago

    I gave it a choice of "Foo" and "Bar" and it scored "Foo" at 98% percent. Why not 0% for both?

      lukasbm 19 minutes ago

      Because it's forced to rate them, there's should be a separate uncertainty parameter for both.

      hanspagel 17 minutes ago

      Did you try Tabs and Spaces?

  • airza 20 minutes ago

    I really hate the way that LLMS design websites.

  • colesantiago 37 minutes ago

    This is true Jevons Paradox (hence the Jev name) there will be so many usecases, applications and even new jobs out of this.

    Learned also that Jev was trained on 100%(!) synthetic data.

    What a great time to be alive.