conv.

All stories
AIActive today · day 7

Open-source Jev clones proliferate weeks after TypeSafe's launch

Multiple implementations of decision models flood GitHub as developers race to replicate TypeSafe's fast, single-pass classification approach.

What to know

  • At least five open-source decision-model implementations appeared within four days (Ollaya, TinyJev, Valen, Nanojev, GLM-5.3-Flash variant), all claiming to replicate or improve on TypeSafe's Jev.
  • The rapid copying has sparked debate: some dismiss decision models as trivial wrappers; others defend them as genuinely novel; most agree the real moat lies in the RL training data pipeline, not architecture.
  • Ollaya emerged as the most polished alternative with API compatibility, multiple model variants, and sub-20ms latency, potentially accelerating TypeSafe's commoditization.
  • Unresolved: whether Laya existed before Jev's public launch, whether decision models are materially different from re-rankers, and whether TypeSafe's competitive advantage survives perpetual open-source parity.

The dispute Is Jev's innovation a durable competitive advantage (requiring the training data/RL pipeline to replicate), or are the architecture and scripts trivial, making open-source parity a death knell for TypeSafe's business model? · positions read across 67 posts and comments

some voices

Decision models are genuinely novel and valuable despite rapid OSS copying; the training pipeline and ongoing innovation are the durable moat.

  • “For everyone dismissing Jev's innovation as being trivial, no it's not. It is definitely not the MNIST classifier you had trained in 2019.”

    fooker · Hacker News ↗
many voices

The core architecture is trivial to copy; OSS replication within weeks proves the innovation isn't defensible and questions whether TypeSafe has a sustainable business.

  • “I'm not sure what this means for AI startups if their innovations can be copied by OSS so quickly (what, like 2 weeks?). There's "consumer surplus" for everyone, to borrow an economic concept. But we do ideally want some of the surplus to…”

    pradn · Hacker News ↗
many voices

Unclear what decision models solve; the use cases and advantages over existing techniques (re-rankers, structured output, fine-tuning) are not compellingly demonstrated.

  • “I installed it, I tried the examples, it works.... But forgive my lack of imagination... what is this useful for?”

    solaire_oa · Hacker News ↗
some voices

Performance quality varies; Laya (and other OSS variants) underperform Jev on real workloads, suggesting the originator's edge is still meaningful.

  • “Has anyone actually seen better or the same results with Laya compared to Jev? From my experience, Laya performs significantly worse. It's less confident and often makes wrong decisions with more complex queries.”

    george_max · Hacker News ↗

TypeSafe Creator of Jev decision modelOllaya maintainers Open-source implementation leadsTinyJev maintainers Open-source implementation leadsValen authors Multimodal extension developers

Open-source Jev clones proliferate weeks after TypeSafe's launch
github.com

How it unfolded 9 developments, newest first · click a bar or a number to jump postscomments

Peak 8 pieces in two hours at Sep 21, 3 AM; 87 pieces over 7 days (3 articles · 17 posts · 67 comments) Sep 21, 3 AM — 8 pieces · 2 articles · 2 posts · 4 comments — Hacker News 5, Newswires 2, Mastodon 1Sep 21, 5 AM — 2 pieces · 1 post · 1 comment — Hacker News 1, Mastodon 1Sep 21, 7 AM — 2 pieces · 2 comments — Hacker News 2Sep 21, 9 AM — 5 pieces · 5 comments — Hacker News 5Sep 21, 11 AM — 5 pieces · 1 post · 4 comments — Hacker News 4, Mastodon 1Sep 21, 1 PM — 3 pieces · 3 comments — Hacker News 3Sep 21, 3 PM — 1 piece · 1 comment — Hacker News 1Sep 21, 5 PM — quietSep 21, 7 PM — 3 pieces · 3 comments — Hacker News 3Sep 21, 9 PM — 1 piece · 1 comment — Hacker News 1Sep 21, 11 PM — 2 pieces · 2 comments — Hacker News 2Sep 22, 1 AM — quietSep 22, 3 AM — 2 pieces · 2 comments — Hacker News 2Sep 22, 5 AM — quietSep 22, 7 AM — quietSep 22, 9 AM — 1 piece · 1 post — Hacker News 1Sep 22, 11 AM — 1 piece · 1 post — Hacker News 1Sep 22, 1 PM — 1 piece · 1 post — Hacker News 1Sep 22, 3 PM — quietSep 22, 5 PM — 1 piece · 1 post — Hacker News 1Sep 22, 7 PM — quietSep 22, 9 PM — quietSep 22, 11 PM — quietSep 23, 1 AM — quietSep 23, 3 AM — quietSep 23, 5 AM — quietSep 23, 7 AM — quietSep 23, 9 AM — quietSep 23, 11 AM — quietSep 23, 1 PM — quietSep 23, 3 PM — quietSep 23, 5 PM — quietSep 23, 7 PM — quietSep 23, 9 PM — quietSep 23, 11 PM — quietSep 24, 1 AM — quietSep 24, 3 AM — quietSep 24, 5 AM — quietSep 24, 7 AM — quietSep 24, 9 AM — quietSep 24, 11 AM — quietSep 24, 1 PM — quietSep 24, 3 PM — quietSep 24, 5 PM — quietSep 24, 7 PM — 1 piece · 1 post — Hacker News 1Sep 24, 9 PM — quietSep 24, 11 PM — quietSep 25, 1 AM — quietSep 25, 3 AM — quietSep 25, 5 AM — quietSep 25, 7 AM — quietSep 25, 9 AM — quietSep 25, 11 AM — quietSep 25, 1 PM — 4 pieces · 1 post · 3 comments — Hacker News 4Sep 25, 3 PM — 2 pieces · 2 comments — Hacker News 2Sep 25, 5 PM — 8 pieces · 8 comments — Hacker News 8Sep 25, 7 PM — 4 pieces · 4 comments — Hacker News 4Sep 25, 9 PM — quietSep 25, 11 PM — 1 piece · 1 comment — Hacker News 1Yesterday, 1 AM — 1 piece · 1 comment — Hacker News 1Yesterday, 3 AM — 1 piece · 1 comment — Hacker News 1Yesterday, 5 AM — quietYesterday, 7 AM — 2 pieces · 2 comments — Hacker News 2Yesterday, 9 AM — quietYesterday, 11 AM — 6 pieces · 1 article · 1 post · 4 comments — Hacker News 5, Newswires 1Yesterday, 1 PM — quietYesterday, 3 PM — quietYesterday, 5 PM — 1 piece · 1 post — Hacker News 1Yesterday, 7 PM — 2 pieces · 1 post · 1 comment — Hacker News 2Yesterday, 9 PM — 6 pieces · 1 post · 5 comments — Hacker News 5, Lobsters 1Yesterday, 11 PM — 3 pieces · 3 comments — Hacker News 3Today, 1 AM — quietToday, 3 AM — 1 piece · 1 comment — Hacker News 1Today, 5 AM — 1 piece · 1 post — Hacker News 1Today, 7 AM — 2 pieces · 1 post · 1 comment — Mastodon 1, Hacker News 1Today, 9 AM — 1 piece · 1 comment — Hacker News 1Today, 11 AM — quietToday, 1 PM — 1 piece · 1 post — Hacker News 1Today, 3 PM — quietToday, 5 PM — 1 piece · 1 comment — Hacker News 1 1–234–789
Sep 22Sep 23Sep 24Sep 25yesterdaynow · 7:01 PM ET
  1. 9

    Adaptation of GLM-5.3-Flash published as Jev-style decision model

    Another OSS variant emerges, this time adapting Alibaba's GLM-5.3-Flash into a System One decision model via PrivateMode's blog.

    “I can't wait for a version of this to come along that supports images. I want to build a feature into Digital Carrot for creating AI goals where you can create a daily goal to, for example, "empty the dishwasher" that you would then verify by taking a picture of the empty dishwasher at the end of the day.”
    — newswangerd, Hacker News commenter · source
    1. first by HN Frontpage, 1d ago

    • I imagine it’s not so hard to optimize a model for this use case.Off the top of my head, I would skip all the modern linear attention / state space stuff and use classical attention. But run prefill in a fully sliding-window mode so that “state” tokens simply don’t attend to far away tokens, or maybe also allow everything to attend to the first…

      amlutoHacker News20h agoview on Hacker News ↗
    2 more of the top 3 · 17 posts in this stretch
    • I have run tests with qwen 3.8 and gemma 4 in a way similar to this post (based on an open source project that also does this with gemma4).Getting competitive accuracy with Jev is fairly easy, if by accuracy you mean that the highest weighted answer is the right one. GLM 5.3 is complete overkill, much smaller llms will doWhat Jev brings to the…

      wongarsuHacker News9h agoview on Hacker News ↗
    • 20k tok/sec prefill on B200/B300 isn't particularly noteworthy for medium-sized models like GLM-5.3-Flash, vLLM and SGLang achieve it on a reasonable number of models, especially at NVFP4.50k tok/sec is pretty impressive though.But... when you were doing your measurements, were you using the same random book excerpt? If you were potentially…

      reissbakerHacker News1h agoview on Hacker News ↗
    all of them →
  2. 8

    Commenter questions whether Laya predates Jev announcement

    A user raises the possibility that Laya (or its predecessor) shipped before or independently of Jev, challenging the narrative that OSS copied the commercial product in two weeks.

    • > I'm not sure what this means for AI startups if their innovations can be copied by OSS so quickly (what, like 2 weeks?).My thoughts too. It sounds like a minor feature being framed as a whole new business.Then again, Dropbox and Docker are too.

      locknitpickerHacker News1d agoview on Hacker News ↗
    1 more of the top 2 · 3 posts in this stretch
    • Didn't llaya come first? So the entire Jev's innovation is encapsulating idea in a cheap service?

      scotty79Hacker News1d agoview on Hacker News ↗
    all of them →
  3. 7

    Observers pinpoint training pipeline, not architecture, as real moat

    Commenters argue that the RL synthetic data pipeline and training methodology—not the model architecture—represents the defensible innovation, and that open-sourcing those would be the true competitive threat.

    “The moat is the RL synthetic data pipeline they set up to train jev. Open sourcing that would be the coup, not the model architecture and training scripts, which are trivial.”
    — _menelaus
    • I think the idea of a "feature startup" is dead. What used to be a niche subscription business is now an individual Epic level of work. The smallest viable business becomes what two or three years ago was a mid tier enterprise. It is no longer "look at this tool I maintain", but "we take this specific approach using these hundreds of tools merged…

      FordecHacker News1d agoview on Hacker News ↗
    2 more of the top 3 · 6 posts in this stretch
    • Today we might need to evaluate “innovation” in a new standard, and have a different expectation for what innovator would be awarded. Getting public attention in such an era where innovation happens every a few days could’ve already been something precious. And that attention would allow TypeSafe to be heard easily next time. Like OpenAI…

      tukHelixHacker News1d agoview on Hacker News ↗
    • For everyone dismissing Jev's innovation as being trivial, no it's not.It is definitely not the MNIST classifier you had trained in 2019.The difference is that you only train it once and the modern LLM machinery sort of takes care of that with large contexts.It's great that Jev proved this is a viable product. I'd expect a great many research…

      fookerHacker News1d agoview on Hacker News ↗
    all of them →
  4. 6

    Analysts warn rapid open-source copying threatens startup defensibility

    Community members note that OSS implementations replicated the core innovation within two weeks, questioning what moat TypeSafe retains and whether the business model survives if competitors copy perpetually.

    “I'm not sure what this means for AI startups if their innovations can be copied by OSS so quickly (what, like 2 weeks?). There's "consumer surplus" for everyone, to borrow an economic concept. But we do ideally want some of the surplus to flow to the innovator, too.”
    — pradn
    • I'm not sure what this means for AI startups if their innovations can be copied by OSS so quickly (what, like 2 weeks?). There's "consumer surplus" for everyone, to borrow an economic concept. But we do ideally want some of the surplus to flow to the innovator, too. I know there were precursors, but that's fine - it's hard to have a totally novel…

      pradnHacker News2d agoview on Hacker News ↗
    2 more of the top 3 · 8 posts in this stretch
    • Because what they did is kinda trivial. Its basically like the Dropbox comment really[0], except here you don't need petabytes of storage and infinite VC pockets.After chatgpt everything in AI mostly became LLMs and building wrappers around them. It's like people forgot how to do ML.To those of us who actually trained models back in the day, its…

      redox99Hacker News2d agoview on Hacker News ↗
    • I installed it, I tried the examples, it works.... But forgive my lack of imagination... what is this useful for?Like, their example is of classification for a support interface.... `refund_requested`. Pretty convenient bool given the example is about a refund- what if 99% of submissions don't ask about a refund? Also, is that user not a…

      solaire_oaHacker News2d agoview on Hacker News ↗
    all of them →
  5. 5

    Community questions distinguish decision models from existing re-rankers

    Developers debate whether decision models are genuinely novel or simply re-branded re-rankers with better probability calibration, with questions raised about what differentiates them architecturally.

    • Guys I have a real q, what is the difference between an instruct based re-ranker and laya/jev I just don't see it.Edit: One is that jev/laya are tuned to have better probabilities, but a reranker can be fine tuned to do that as well. And jev/laya use RLCD?

      alex7oHacker News2d agoview on Hacker News ↗
    1 more of the top 2 · 2 posts in this stretch
    • It would be really cool to have LLMs and System One in a single tool - in this case, if Ollama implemented it.

      mococaHacker News2d agoview on Hacker News ↗
    all of them →
  6. 4

    Ollaya launches as full-featured local decision-model framework

    The most polished open-source implementation arrives with four model variants (laya, decider, von, qwen3guard), desktop and CLI tools, Docker support, and API compatibility with TypeSafe's SDKs. Achieves 10ms latency on RTX 4090 for five-question requests.

    “Ask typed questions about any text or JSON and get calibrated answers in milliseconds. Private, open source, on your own hardware.”
    — Ollaya documentation
    • Has anyone actually seen better or the same results with Laya compared to Jev? From my experience, Laya performs significantly worse. It's less confident and often makes wrong decisions with more complex queries.

      george_maxHacker News2d agoview on Hacker News ↗
    2 more of the top 3 · 3 posts in this stretch
    • Cool... but this does seem undermined by the fact that Ollama can add support for decision models at any time.

      emmettbtHacker News2d agoview on Hacker News ↗
    • >Run decision models locally.>example is a text classification task instead of a decision

      ranyumeHacker News2d agoview on Hacker News ↗
    all of them →
  7. 3

    Valen extends decision models to images and video

    A multimodal variant emerges, adding visual perception to the System One decision pattern with Qwen3.5-0.8B and 2B backbones, solving visual puzzles in ~9 decisions with 1.13 seconds latency.

  8. 1 day quiet
  9. 2

    TinyJev launches with two model sizes, offline-capable

    TinyJev released with 0.6B and 4B parameter sizes, runs entirely offline on MLX (Apple) and PyTorch, achieving 86ms per question on base M1 versus GPT-6 Sol's 2,042ms on the same benchmarks.

    “TinyJev scores every option of every question in a single forward pass and returns all twelve together, 596 ms, 10 of 12 right. GPT-6 Sol writes the same twelve as JSON: 2,198 ms, 12 of 12 right.”
    — TinyJev documentation, Project benchmark · source
  10. 1

    Nanojev released as minimal 200-line Jev clone

    A stripped-down, single-file implementation of decision models appears on GitHub, demonstrating the concept can be reproduced in minimal code.

What people are saying 14 voices from 1 site · best of 67 · verbatim

Still unanswered
  • Does Laya predate Jev's public announcement, or was it genuinely developed in response?
  • How materially different is a decision model from a fine-tuned re-ranker or classifier with probability calibration?
  • What happens to TypeSafe's business if Ollaya or another OSS tool achieves parity on latency and accuracy?