Quite impressed by the energy people are putting into making OSS Jev-like models.
I understand the hype but I wonder: what are the use cases for this kind of model? Could it be used in the context of coding agents, or is it more relevant in totally different situations?
To develop a smart ai system for my 2d roguelike platformer?
game has way too many moving system for classic state-machine ai + i cant spare the time to develop it.
its low latency entices me.
Consider every situation where you "force" an LLM to output only a choice / category, or a set of them. If you have workflows like that, you're now being promised significant cost- and latency reduction.
For coding agents it'd only be useful in a subset of situations. E.g. you could imagine using one to classify bash tool calls into safe and unsafe for example.
what are the use cases for this kind of model? Could it be used in the context of coding agents
Yeah, it could. The most obvious usage would be to have local fast cheap "feedback" / "control" over a slower more expensive agent (i.e. cc / codex / opencode). Things like "goals" could now be split from a long prompt into "actions" and "verifiers". Where for each action you also produce a verifier. Then after each action you run the verifier w/ this kind of "universal classifier" and decide if the step was done correctly, if it needs follow-up and so on.
Example: implement auth in this repo -> llm_plan() -> for item in plan generate_verifier() -> for item in plan implement() ; verify() ; accept() / followup().
Verifiers could be something like this. take a plan item as input, generate classification questions that might verify the task "is this following project conventions?" | "is this touching files from other tasks?", etc.
You can do that with LLMs, but some things might become cheaper / faster. And you can pretty much use it to check against an ever growing list of conventions. Yours or project specific.
Bit of a Jev explosion going on. Is it because it's taking us back to a simpler time we understand better? Classification models have been around for a while.
It's because everyone wants their 15 minutes of fame so every single time something shiny gets out all the NPCs are asking astra/fable: "can you create a copy of this, make no mistake"
Thanks to these projects, what was an innovative-but-closed piece of technology one week ago is now much more accessible. Whether they're in it for fame or not, I couldn't care less!
and enabled things that were impractical previously
I think that there are not _that_ many use-cases that have been opened up by this that tool-calling on other models didn't solve already. Really depends what benchmark you're looking at. This one against BANKING77[0] has many issues, but suggests it's really not far off DeepSeek 4.1 Flash. This one against BoolQ[1] shows marginal improvement over Qwen3.6. This one against MMLU-Pro[2] (same author as the previous) shows significant improvements over two Qwen models.
So there's definitely _some_ alpha there, but I don't think it's the sea-change that the hype would suggest; that is to say, yes, some things that weren't practical before are now, but many things were already very practical with the existing tools.
It reminds me a bit of what Ansible got right: user communication. The underlying tech may have existed for a long time, but the genius is presenting it to a regular developer in a way that reads "yes, even you can understand ML, just using a little JSON". The contribution of that should not be understated, as has been clearly evident recently.
The way I see this (I havent played around with Jev or layla the OSS version) is that classifiers have always existed and a recognised tool in the ML world. But, the norm is that one needs to not only know what to classify as, but determine what weights to use to classify the input.
Jev came in, and added that magic of "you dont need to train your classifier or determine the weights" if you dont want to, and just get the classified answer out. I think that's what is making people see this with a glitter in their eyes.
I think a great use case for these will be when they have large context windows and are able to enforce styling rules for frontend development, and component creation rules for react. You can then ditch the styles guides and styling skills and create a decision tree for enforcing styling, so that you can't run into drift issues or duplication issues. That's where I'm wasting most of my time right now, constantly correcting all of the UX/UI issues that are created for every single feature.
Back in the good old days we would prevent these ux/ui issues by rigorously enforcing the use of our own stylesheets and classes. Later that grew to only using the company ux components. This was very successful in keeping everything neat and tidy. The only drawback was creating and curating new elements and getting consensus. But otherwise it works wonders.
Try constructing reusable components out of what you are doing instead of building everything up from basic building blocks. This also allows more concrete testing of individual parts and then if you want to change the look you can change it in one place and have it apply everywhere.
Agentic development doesn’t mean “throw all what we learned out of the window”, the same practices that helped speed up and improve quality of work of humans also helps agents. In fact, the multiplier is even bigger. You will notice it in development speed and reduced cost due to avoiding churn.
Because these decision models do not have tool calling, the knowledge cutoff might become a problem. We'll either have to keep training continuously if we run locally or switch to the newer version every month or so when using a closed one like Jev
even with knowledge cutoff set a second from now, you still want to provide as much info as you can if you’re using such tools for delegating decisions
I wonder how these would do filtering my spam. I have been using 27B-class models for a while now, and they are nearly perfect at determining what is spam and what isn't. The only disadvantage is computational cost.
Take a look at Thomson 1.0-small, which is a variant of qwen 3.6 35b post trained by Thomson Reuters for text analysis. It classifies text content very well.
On Gemma 4 12B, I am getting 220 ms per move or QS. I used it to play the Snake game locally:
prompt_eval=244 ms wall=245 ms schema_cache=hit generated=0
Move limit reached after 200 moves: score=16, length=19.
So, if a 12B dense model can offer this latency on a local old PC, then definitely you can scale it up with more powerful machines and get even lower latency.
Can someone do a ELI5A of how they achieve classification over any user defined list of items? Normal neural networks do a softmax over a known output set to get probabilities
The bright side of Jev being so popular could be that many companies and individuals realize that their applications might work well with a System One model, and they decide to run an open-source (or fine-tuned) version on their own
Been hoping for something in this space. Jev-like decision models on Qwen3.5 could really simplify some of our internal routing logic.
Quite impressed by the energy people are putting into making OSS Jev-like models.
I understand the hype but I wonder: what are the use cases for this kind of model? Could it be used in the context of coding agents, or is it more relevant in totally different situations?
Yeah same. Got access to their API and then realised I don’t really have an immediate use case
You should call Jev-like models when you give it a JSON-like structure to produce, it is useful when you need _some_ intelligence in your code.
To develop a smart ai system for my 2d roguelike platformer? game has way too many moving system for classic state-machine ai + i cant spare the time to develop it. its low latency entices me.
Consider every situation where you "force" an LLM to output only a choice / category, or a set of them. If you have workflows like that, you're now being promised significant cost- and latency reduction.
For coding agents it'd only be useful in a subset of situations. E.g. you could imagine using one to classify bash tool calls into safe and unsafe for example.
Yeah, it could. The most obvious usage would be to have local fast cheap "feedback" / "control" over a slower more expensive agent (i.e. cc / codex / opencode). Things like "goals" could now be split from a long prompt into "actions" and "verifiers". Where for each action you also produce a verifier. Then after each action you run the verifier w/ this kind of "universal classifier" and decide if the step was done correctly, if it needs follow-up and so on.
Example: implement auth in this repo -> llm_plan() -> for item in plan generate_verifier() -> for item in plan implement() ; verify() ; accept() / followup().
Verifiers could be something like this. take a plan item as input, generate classification questions that might verify the task "is this following project conventions?" | "is this touching files from other tasks?", etc.
You can do that with LLMs, but some things might become cheaper / faster. And you can pretty much use it to check against an ever growing list of conventions. Yours or project specific.
Bit of a Jev explosion going on. Is it because it's taking us back to a simpler time we understand better? Classification models have been around for a while.
It's because everyone wants their 15 minutes of fame so every single time something shiny gets out all the NPCs are asking astra/fable: "can you create a copy of this, make no mistake"
Thanks to these projects, what was an innovative-but-closed piece of technology one week ago is now much more accessible. Whether they're in it for fame or not, I couldn't care less!
It’s because it’s practically useful and enabled things that were impractical previously.
I think that there are not _that_ many use-cases that have been opened up by this that tool-calling on other models didn't solve already. Really depends what benchmark you're looking at. This one against BANKING77[0] has many issues, but suggests it's really not far off DeepSeek 4.1 Flash. This one against BoolQ[1] shows marginal improvement over Qwen3.6. This one against MMLU-Pro[2] (same author as the previous) shows significant improvements over two Qwen models.
So there's definitely _some_ alpha there, but I don't think it's the sea-change that the hype would suggest; that is to say, yes, some things that weren't practical before are now, but many things were already very practical with the existing tools.
0: https://sanand0.github.io/llmevals/jev/
1: https://github.com/ekzhang/openjev-sglang/blob/a3554ed9e9c26...
2: https://github.com/ekzhang/openjev-sglang/blob/a3554ed9e9c26...
It's appealing not having to fine-tune separate model for each use case
So you have more flexibility to get on with building, evolve your business logic etc
It reminds me a bit of what Ansible got right: user communication. The underlying tech may have existed for a long time, but the genius is presenting it to a regular developer in a way that reads "yes, even you can understand ML, just using a little JSON". The contribution of that should not be understated, as has been clearly evident recently.
The way I see this (I havent played around with Jev or layla the OSS version) is that classifiers have always existed and a recognised tool in the ML world. But, the norm is that one needs to not only know what to classify as, but determine what weights to use to classify the input.
Jev came in, and added that magic of "you dont need to train your classifier or determine the weights" if you dont want to, and just get the classified answer out. I think that's what is making people see this with a glitter in their eyes.
- https://github.com/logan-markewich/jeff - https://github.com/bespokelabsai/nimble
Why does nobody ever ship these as a docker image?
I guess you have AI to write your docker files and push your images now.
I think a great use case for these will be when they have large context windows and are able to enforce styling rules for frontend development, and component creation rules for react. You can then ditch the styles guides and styling skills and create a decision tree for enforcing styling, so that you can't run into drift issues or duplication issues. That's where I'm wasting most of my time right now, constantly correcting all of the UX/UI issues that are created for every single feature.
Back in the good old days we would prevent these ux/ui issues by rigorously enforcing the use of our own stylesheets and classes. Later that grew to only using the company ux components. This was very successful in keeping everything neat and tidy. The only drawback was creating and curating new elements and getting consensus. But otherwise it works wonders.
Try constructing reusable components out of what you are doing instead of building everything up from basic building blocks. This also allows more concrete testing of individual parts and then if you want to change the look you can change it in one place and have it apply everywhere.
Agentic development doesn’t mean “throw all what we learned out of the window”, the same practices that helped speed up and improve quality of work of humans also helps agents. In fact, the multiplier is even bigger. You will notice it in development speed and reduced cost due to avoiding churn.
Because these decision models do not have tool calling, the knowledge cutoff might become a problem. We'll either have to keep training continuously if we run locally or switch to the newer version every month or so when using a closed one like Jev
even with knowledge cutoff set a second from now, you still want to provide as much info as you can if you’re using such tools for delegating decisions
I wonder how these would do filtering my spam. I have been using 27B-class models for a while now, and they are nearly perfect at determining what is spam and what isn't. The only disadvantage is computational cost.
Take a look at Thomson 1.0-small, which is a variant of qwen 3.6 35b post trained by Thomson Reuters for text analysis. It classifies text content very well.
On Gemma 4 12B, I am getting 220 ms per move or QS. I used it to play the Snake game locally:
prompt_eval=244 ms wall=245 ms schema_cache=hit generated=0
Move limit reached after 200 moves: score=16, length=19.
So, if a 12B dense model can offer this latency on a local old PC, then definitely you can scale it up with more powerful machines and get even lower latency.
Can someone tell me what is the difference between Jev and a normal neural network that does classification ?
My understanding is: it takes text input and it does one shot classification (no training data)
Yes, this is essentially it.
As a corollary, the output classes can be any set, rather than needing to be set before training.
Can someone do a ELI5A of how they achieve classification over any user defined list of items? Normal neural networks do a softmax over a known output set to get probabilities
Interesting approach with Qwen3.5 for decision models. Curious how "tiny" they've made them while keeping LLM reliability for critical paths.
Interesting to see a Jev-like approach applied to Qwen3.5. Always appreciated Jev's simplicity for quick decisions.
The bright side of Jev being so popular could be that many companies and individuals realize that their applications might work well with a System One model, and they decide to run an open-source (or fine-tuned) version on their own
Why not name it Qev?
Oh Jared is cool - he made After and Razzle - nice