Laya beats Jev with 33ms open-source decision engine
Laya the open source version of Jev
Laya is an open-source System 1 decision engine that runs in 32.8 milliseconds on a single GPU, 6 to 8 times faster than TypeSafe Jev. It uses bidirectional encoders and three primitives—choice, score, and noul—to deliver calibrated probabilities without generating text, making hallucinations impossible. The model family includes three checkpoints for English, 100+ languages, and typed decisions, all under Apache 2.0. Benchmarks show Laya outperforms Jev on accuracy, calibration, and latency, with zero API costs.
The model's own confidence gives no warning when it cannot read the input script.
- prometheus1992
I think the main gripe that people had with Jev and Typesafe was the language used when they launched. To me personally it seemed like a parody/con/shady at first.
"Breakthrough", "our research went in another direction" , "Two years in stealth", "System One thinking model", "Jev can't hallucinate", "RLCD","We are doing very cool stuff, but we will have to hire you to tell you", - these are some of the things that they said on their website on the launch blog.
I had used versions of bert to achieve the same functionality years ago. But to me it seems like they were able to trick the VCs with "can't hallucinate" etc.
To the above author, kudos for sharing your work and making it open. Something like this shouldn't be closed in the first place when it has been available for so many years
- Oras
I played around with Jev last night and did it for classification tasks that I used Gemini 2.5 flash lite with.
It’s a bit faster and bit cheaper, but this is compared to LLM. The consistency was nice to see, BUT, as someone who trained NLP models prior to LLMs, it’s just BERT with more data. I can see why people would want ready made one shot classifier, and I can see the value of sending multiple classifier in one call, but I wouldn’t call it breakthrough. And I believe many labs will replicate it in no time and might have it as part of their harness.
I see it as a wake up call for the tech community to go back to basics for most tasks instead of relying solely on generic LLMs.
- dcow
I can understand why the author feels bitter but it still feels juvenile to me. Certainly both Jev and Laya are based on the research of countless prior papers and academics. Diogo decided to build a product out of the concept. The author didn't. Publishing research papers and model weights is probably part of the problem--it feels academic. If you look at the author's profile they focus on applying AI to healthcare. Not selling general AI type safety to AI pilled companies and devs. There's a big difference there. Whether that's good or bad you can argue all day. But for the author to expect otherwise is pretty weird. I do applaud them for not stewing too much on it and trying to do something about it, though.
- kamranjon
It is really interesting to see this claim, because i thought the current theory was that typesafe actually repackaged the work from GLiNER[1] - which does seem to be a closer match, and their original paper[2] predates yours by several years. Curious if you had heard of it before? It is also open source[3] and I think also has some good usage.
[1] https://arxiv.org/abs/2507.18546
- wren6991
We've all seen "this meeting could have been an email"; now get ready for "this VC-backed firm could have been a single arXiv preprint."
I don't want to be too dismissive of Jev, but building technology in stealth for two years just doesn't make sense to me when the capabilities are so easily replicated. These are strange times, where the incentive to do public research and the incentive to develop in private are both being eroded.
- baobabKoodaa
Jev claims to be frontier intelligence. Laya, while claiming to be "the open source version of Jev", is using a tiny open weight model with a tiny context window. Anyone who has experimented with tiny models knows that they are far from "frontier intelligence". It's not plausible that Laya could be "the open source version of Jev", with "frontier intelligence", when it is using these tiny models.
Also, the paper that OP is referring, is not describing anything that sounds like a generalist classifier (which is what Jev is). Their paper describes a tailored solution to one specific business problem. I'm sure it has some similarities with Jev, but it's still a completely different thing, and I'm confused why OP is claiming it to be the same thing.
If you don't believe me, just open the PDF and read the abstract.
- hmokiguess
I think the biggest lesson with Jev was the one of communication and understanding for the broader audience, sometimes a lot about innovating involves repeating yourself and translating your own thoughts to an intended audience.
Classical machine learning has been, for the most part, and just by the nature of science, behind academic terms and difficult to engage with as a product.
Jev did really well with coining up “System One” models and defining a standard application interface plus core primitives that landed in the current paradigm of software development.
I think it’s sort of like how Cursor reinvented autocomplete back then as a different UX and suddenly everyone was just using it because of how easy the bar was to understanding it.
Lastly, timing is everything. Just as Cursor had a first mover advantage, despite ML Ops being a thing for a while, they managed to encapsulate the concept behind a “System One” black box that fits the existing mental model for building software and shipping a data contract in the right point in time where the cost of tokens has been an important metric to watch.
- mixedbit
The unfortunate true is that getting even the best work in front of an audience is often much harder than solving the problem. Is uploading a paper to arXiv enough to expect the work to be recognized and cited? Unfortunately, it rather is not. arXiv is an open repository which includes plenty of not reviewed and not officially published papers. In a popular field such as machine learning, the number of arXiv papers is overwhelming. Expecting that some machine learning expert will stumble upon an arXiv paper and recognize its value is wishful thinking.
I'm not a researcher, but long time ago I had an idea of a new, seemingly interesting attack on TCP. Having some free time between jobs, I wrote a paper about this, created a proof of concept and decided to send the paper to USENIX Security. I got back two reviews, both in rather positive tone, but rejecting the paper on the grounds that it shows only individual steps of the attack, but it would be much stronger if it showed also the attack working end-to-end. At that point I just uploaded the paper to arXiv and called it a day. I've put a lot of work into that paper, but not enough, I don't consider it properly published and I don't expect anyone to cite it. The paper failed the peer review process and I didn't put the work to improve it further.