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.
Love it. I was really surprised to see the traction typesafe got in the first place. I had built something similar a year ago for a client and thought it was nothing groundbreaking. The client bought it, still uses it and that was it. I had also spent considerable time training and fine tuning zero shot NLI classifiers. Anyway, after typesafe was launched I decided to start building this open source library - https://github.com/deepanwadhwa/OpenDecision . The context length for the underlying model is 8k.
Quickly reading the article, one notable limitation seems to be that these checkpoints are 512-1024 tokens context size models, while Jev is seemingly 32k.
That's a pretty big limitation, I would argue, unless I'm misunderstanding and it can be worked around easily somehow? I'm surprised it isn't surfaced more prominently in the comparison.
I've been deeply impressed with Jev as it made a bunch of workloads we had on Luna or Gemini 10x cheaper and 2x faster (previously used non reasoning version for latency reasons).
Now Laya promises another speed up and it's open source. Tbh if it can't run on a CPU I anyway want to buy it from an inference provider. Managing gpus in production is a non trivial problem.
What I also wondered about Jev is how different it is from something like tabular foundation models. They seem to overlap in use cases. Which then leads to the question, what is actually learned? A lot of people in machine learning spend time to making things explainable and always struggled to move beyond data induced biases.
Having it open source is awesome as fine tuning might give additional performance on the task we care about.
Jev was built using the same architecture Laya's author proposed[1] in March 2025. Laya is an open-source system based on that research from a year ago. Whether Jev is also based on the OP's materials or independently invented is hard to say.
No, OP thinks they independently discovered Jev's architecture a year ago and published a paper. I am not an expert but I don't think Typesafe has published Jev's architecture so OP's claims cannot be taken at face value.
It’s the other way around for me. OP has published everything in the open, so I can take him at face value. A PR media release on the other hand, I can accept with some reservations. The objective and non-conspiratorial reading I could offer is, this is most probably two independent discoveries of the same idea, maybe with different implementation. I still think the Jev team should look at prior art before going so hard on the marketing.
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.
Love it. I was really surprised to see the traction typesafe got in the first place. I had built something similar a year ago for a client and thought it was nothing groundbreaking. The client bought it, still uses it and that was it. I had also spent considerable time training and fine tuning zero shot NLI classifiers. Anyway, after typesafe was launched I decided to start building this open source library - https://github.com/deepanwadhwa/OpenDecision . The context length for the underlying model is 8k.
Quickly reading the article, one notable limitation seems to be that these checkpoints are 512-1024 tokens context size models, while Jev is seemingly 32k.
That's a pretty big limitation, I would argue, unless I'm misunderstanding and it can be worked around easily somehow? I'm surprised it isn't surfaced more prominently in the comparison.
I've been deeply impressed with Jev as it made a bunch of workloads we had on Luna or Gemini 10x cheaper and 2x faster (previously used non reasoning version for latency reasons).
Now Laya promises another speed up and it's open source. Tbh if it can't run on a CPU I anyway want to buy it from an inference provider. Managing gpus in production is a non trivial problem.
What I also wondered about Jev is how different it is from something like tabular foundation models. They seem to overlap in use cases. Which then leads to the question, what is actually learned? A lot of people in machine learning spend time to making things explainable and always struggled to move beyond data induced biases.
Having it open source is awesome as fine tuning might give additional performance on the task we care about.
This project was built on the exact research on jev architecture research one year ago
I don't understand this sentence, can you try again please? Are you saying Laya was built on research done by the Jev team?
Jev was built using the same architecture Laya's author proposed[1] in March 2025. Laya is an open-source system based on that research from a year ago. Whether Jev is also based on the OP's materials or independently invented is hard to say.
[1] https://arxiv.org/abs/2503.23303
No, OP thinks they independently discovered Jev's architecture a year ago and published a paper. I am not an expert but I don't think Typesafe has published Jev's architecture so OP's claims cannot be taken at face value.
It’s the other way around for me. OP has published everything in the open, so I can take him at face value. A PR media release on the other hand, I can accept with some reservations. The objective and non-conspiratorial reading I could offer is, this is most probably two independent discoveries of the same idea, maybe with different implementation. I still think the Jev team should look at prior art before going so hard on the marketing.