I’ll go out on a limb and suggest that I don’t think a Jev-like model is particularly useful unless you can fine tune it. The Jev API has zero ability to pass in a prior [0], and, if you can neither pass in a prior nor fine tune for your system, you will get an output that may be almost meaningless.
I’d love to see someone build a model of this sort that can actually accept priors and do something intelligent with them.
[0] You can feed Jev a prior as text. I’ve tried it. It works poorly.
Am I hearing this right, that they made a decision model based on Typesafe's new paradigm, and actually made a model better than Jev based on Typesafe's own ranking?
It's not a "new paradigm", it's a low-hanging fruit that's been lying around for years; Typesafe were the first to bother to stop and pick it up, and market the shit out of it. But it was still a low-hanging fruit.
There are many, many of those left around, because AI frontier is moving forward so fast, everyone is racing ahead. Which is why I laugh when people say AI is not transformative and LLMs are a dead end (and my favorite, "what are we going to do with all those GPUs when the bubble pops?"). Even if SOTA LLMs hit a hard capability limit tomorrow and never advanced again, there's a good decade of growth and advancement to be extracted just from all the low-hanging fruits that were left unpicked along the way.
Diffusion transformers are not "easy" but underfunded.
Random one in terms of applications: getting GPT-4-level[0] LLMs to operate at hundreds of tokens per second on edge hardware - opens up so many possibilities I'm probably unable to imagine half of them.
E.g. Imagine spellcheck/predictive text (or code autocomplete) where the model is able to process a whole paragraph + surrounding application/system context in between keystrokes. Or an OS being able to reliably guess what you're doing in real-time, in between your UI interactions, and offer actually helpful contextual reactions.
Or imagine finally funding some decent studies into exploring the models as computational artifacts - studying their latent spaces, how they form and how they model reality internally.
Or imagine automated sliding doors that don't suck.
--
[0] - Or anything substantially better than BERT-level models used in Jev or that demo from the company doing inference ASICs, that has a chatbot online that does 14 kilotokens per second.
Diffusion models combined with these new looping techniques are gonna change the whole conversation about efficiency. Imagine control net but in one or more conceptual latent spaces.
But also harnesses and more generally new insights on "the control flow problem" could end up squeezing a ton of performance out of small models.
Definitely agree with edge computation, although inference extensively researched and funded if SOTA LLMs hit a dead end tomorrow,there is still a lot to explore and research in inference and edge computation
Enough stuff can happen, software use itself might change, and that could really cause anything. "What will we do with all the gpus" might become a question if for a magnitude of tech and reasons leaked-opus-9 runs on a macbook m6 or 7
Yes. It's well within realm of possibility, but so far wasn't pursued because the Big Vendors went all-in into capability growth (rightfully testing "the bitter lesson" to its limits) and got themselves stuck in an arms race, while everyone else is barely keeping up and/or starstruck with fascination, exploring what these models can do.
This got everyone racing forward and right now there is not enough human attention left in the world to productionize this, or any of the other "side threads". When the race slows down, people will catch up, branch out, and loop back.
They will. That's the fallacy of the "S-curve" everyone likes to commit these days actually giving a positive outlook.
Assuming it won't get to full RSI, the current approach will burn out - most likely economically. The race slows down, people branch out, look back, start picking up the "untapped potential"/low-hanging fruits, and you have new S-curves launching in place of the one that just tapered off (hence a fallacy - a stack of S-curves adds up to continuing exponential growth).
In other words: it comes and goes. Hyperconcentrated capital will eventually deconcentrate.
If we throw in hardware dedicated to a specific LLM, it seems to be a rather low hanging fruit. Especially considering that this is already happening for vision models [1].
Maybe they meant in the sense of “untapped potential”, because so far a lot of the focus has been on increasing model capabilities, not necessarily performance/power budget.
Yes. Point is, it's untapped only because everyone is running in the race (even if out of curiosity), and there's just not enough people with means to tap into these side threads. For the past few years, there's been many interesting papers that circulated the industry, got recognized as worthwhile pursuits, and then dropped because running behind the Big Vendors had massively better ROI.
I can imagine advancements on making smaller models work together better instead of a generalized core. Imagine a community or city having a https://pirateface.co/ so that the shard of the model that you need can be streamed in with minimal latency with your box only holding the minimal version (say deepseek v4 flash as orchestrator) of the model that you use on day to day basis.
We have overcome split brain problems before so this wont be our first
Closely connected to decision models: A good library to do ranking based on pairwise ranking on multiple attributes. By using a decision model (especially one that can make decisions on multiple fields at the same time) this becomes a lot faster and more powerful. Could make for a pretty nice search reranker as well as prioritizer for many problems.
Of course you can also do ranking one-off with a decision model, but this likely less stable, and by doing pairwise ranking you can also relatively quickly do incremental inserts to the list.
The weights have permissive licensing, but the data and training pipeline are not published to reproduce them from their proprietary Qwen starting points. Weights are not "source."
Came directly to comments hoping not to see this one.
<sad trombone sound>
Surely someone will soon do what the title of this post makes it seem like cloudfare did. Truly modular open source training and inference logic, along with a totally open corpus and weights, will eventually out-compete the closed ecosystem.
I found the paragraph about how much networking data they have weird. I mean, if you already have all that data why didn't you train your models already using that? Why did you need clef to begin with?
Clef is based on Qwen3.8-27B and Clef-flash is based on Qwen3.8-9B (edit: actually Qwen3.5-9B). So, similar in spirit to Kev by my understanding, but based on a newer model.
Yes, it's easy. The thing people are missing (especially those believing AI is a "dead end" and "not transformative") is that the field has been advancing so fast in the past few years, that there's lots of such unexplored avenues, unpicked low-hanging fruits, that everyone just raced past. We've barely begun exploring the capabilities ML brought us - patterns, applications, and architectures.
Now that we're hitting against the hardware supply limits of global economy, I expect more people to go back and revisit the things left along the way in the mad rush to "just throw more compute at it / make a bigger model" - and thus many more cases like Jev to show up in the next few years.
The basics are pretty simple. And depending on what your specific need is, the model can be really really basic, fast and super effective (ie. run on a mobile device and process thousands of requests in <100ms)
I've been playing with this for the last year or so. Started with a personal email classifier, also did benchmarks with some public datasets, then created a couple classifiers that could play Doom, and now I've been trying out some other experiments, like a request proxy/router to automatically choose a classifier and fallback to LLM to handle unseen requests
Jev did a great job at creating hype, but also at shaping the concept and space of "decision engine" or "decision model". People were already doing this with LLMs, which is very inefficient for most tasks like that, and the Jev guys figured there was a market there. It seems like they were right, and now there's a rush to flood the space, taking advantage of the hype window
In general, training a general purpose classifier is something lots of people have worked on for a long time. Large Transformer models themselves are typically "generalists" already, so structured generation and constrained decoding have given you the ability to use an LLM as a general classifier for years. It's an incredibly common pattern for working with LLM judges or any sort of branched decision making workflow.
A lot of people who are a bit less familiar with the field saw the hype around Jev and presumed that the reason it was so exciting was that it was a fundamentally new interface for working with an LLM. And that additional excitement drove even more attention to Jev. But fundamentally, TypeSafe's announcement was that they found a particular architecture/training paradigm that resulted in a model for this particular interface that had incredible accuracy, very low latency, and for which they could offer inference at a super low cost.
I've not kept up with the flood of Jev clones that have been released, but I think this is just typical for any new component in deep learning that gets popular. There are an absurd number of open source autoregressive LLMs and fine tunes you can use. The thing that makes one more popular than the other is typically the general performance of the individual model.
But training a model for this purpose, or emulating the procedures described in Jev's papers, isn't something that would be beyond the capabilities of any lab. It's not an entirely alien architecture or approach.
The bigger question for TypeSafe as a company would be if other teams are producing Jev-like models that win on performance or cost. Like I said, I haven't followed the reports super closely, so no idea if that's the case or not.
Yes it's easy for an established shop, all they need to do is to tweak the post-training workflow. "Decision model" is the same kind of marketing as "LRM" attempted by OpenAI when RL CoT was new (to hyped up crowd). It's still fundamentally a classifier used for "decision making", games and RP were using generalist models and constrained outputs to do what the DOOM demo does for years.
What even are these new "decision models?" Take an existing LLM, feed it a prompt, force it to pick a choice; decode is 1 token (or rather, the whole logit set for only that last token; token implies selecting one logit) so you made a choice. That's it?
Yes but optimized specifically for the purpose. Using that for "decision making" is also not a new use case, but turned out to be new to many people. Which is great, I hope they make something cool with it!
The interesting part is also the easy part. The model and architecture are not hard for an experienced machine learning engineer to build.
The hard part is the data and evaluation. Sure, it’s not that hard to build a fast model with good predictive power. But fast at doing what? You probably don’t care about classifying whether a hotdog is a sandwich (which is the Jev demo).
Is there a Jev-like model I can run on my Mac? Something like Ollama? Or what's the best way to play with it? Is there a cheap/free API service eg on OpenRouter?
With all these new Jev-like models popping up, has anyone actually started building anything with them yet? It's odd how quickly they've multiplied despite being relatively niche in their use cases, as far as I can tell. I suppose they're simple and cheap enough to make that it's a sort of 'why not' thing for a lot of these companies.
I wonder if a good usecase for this would be cloudflare's WAF rules. Give broader request context to the decider and let it pick type of challenge/block traffic directly.
Can someone explain how so many folks managed to build decision models within days or weeks after Typesafe came out with Jev? Is this concept of decision models been in the works for a while? Is it easy to copy?
Smaller models have been able to do these sorts of tasks, but a little slower, for a while now. Give a small Qwen 3.8 model a classification task and force a structured output, and it'll do a good job. I've used Qwen 0.8b for basic image classification in <500ms on my local machine for a while now.
There are a few technical details that can reduce the latency significantly (covered in the post) but the real insight has been from watching the reaction to Jev and seeing that there's enough of a market interest to offer it as a distinct thing. The underlying concept/approach was already there.
Not just structured output. Dropping down to logprobs, prompting the model to emit one word as the answer, and then ranking the output tokens to pick your answer works great on small Qwen & Gemma models.
The fascinating part to me is that Jev seems like this technique plus post-training to get multiple independent confidence values for each possible answer.
Transformers output a set of probabilities over outputs. For ChatGPT etc, those are predictions of what the next token will be. But it can also be a structured list of options or classes. Jev mostly innovated on the interface, API, and product concept around this, and made it click for a large number of people. Unfortunately for Jev, it's very easy to copy an API, and any pretrained LLM can be adapted to work in this way.
I think Jev also innovated on data & algorithms, but it remains to be seen if it's enough to be meaningfully better than traditional LLMs + a few tweaks.
Most answers explain the LLM-based approach to these models, which is also what Typesafe did with Jev. However, depending on what you need, there are far simpler classification models, and for a lot of use cases, these models can be way faster and more accurate than Jev
But, for these adhoc models, you need to understand the task more, collect some data and train the model (on CPU, no need for GPU). So Jev-like models are a great way of getting a hosted general decision model, but if you have a very narrow task or set of tasks, you might be better off with some more basic models that you can run on the same server you run other things or even on your laptop
Jev created accessible/programmatic ergonomics around a general purpose classifiers, and did it very well; ie intuitive api and structured data approach.
Anyone can copy that and apply to an array of models - stripped down LLMs or already slim/highly performant traditional classification architectures (just wrap inference with an api that inputs/outputs the same structured data).
Jev, I think, would say their advantage is the intelligence of their models and training data including calibration: https://medium.com/code-applied/calibrated-classifiers-makin... (which i still struggle with in the general application... there's no free lunch with these things).
You can use already trained large transformer models to make one, so it doesn't require the kind of high-scale compute, high quality data, data cleanup, reinforcement, and so on training that say an LLM does.
What's new is "smart" decision models than you can supposedly use on anything without additional training.
If you have a very narrow use case you can train a BERT based decision model on a laptop an hour if you have good data to train it on. It'll answer faster than the roundtrip to clef/jev and use <1gb memory
You just have to fine tune an LLM like Qwen on some synthetic data to do so. There was even someone that had a model that was exactly like Typesafe and published their work a year before Jev (but wasn't marketed as heavily since it was academic).
It's not a new concept, it just took someone adding on to the approach and refining it. I never deep dove it, but I assume JEV is sort of like how Sora works? They had a blog post about how it has a sort of tiny LLM, which OpenAI's small LLMs are insanely good and well defined. I think any lab tackling this with a from-scratch model could yield affordable alternatives that are highly competitive.
It seems insanely obvious at least to me, that JEV is the new hot thing for the AI field since they give you stronger output that isn't... flat out wrong, that alone is impressive.
They are not too difficult to train if you already have infra to train regular LLMs. You can typically replace a few layers train them alone and you're off to the races.
Getting training data that works well for calibrated classification objectives is difficult.
I hear conflicting opinions (including my own) about how well calibrated each of these are. Jev seems to be the best.
But the jev release made obvious the PMF for these models, and the underlying reality is that calibration really doesn't matter much when you're replacing usecases where people were using damn LM head softmax probabilities before, which are nowhere near calibrated.
So now everyone simply finetunes qwen and makes a compared-to-regular-LLM vastly cheaper decision model. And it works for majority of usecases. People mostly only care about accuracy, not confidence.
That's probably driven by their own internal need to show the model images of emails and webpages to detect phishing, despite obfuscation of the underlying HTML.
Yeah, these AI companies have some weird paradox that if they actually had a model that was super efficient and could arbitrage cost/intelligence of other inferior models, they would keep everything about it secret. If an intelligence research group had something groundbreaking, they would just dump their own money into the magic money machine.
Instead, to make up for the lack of economic viability of their models, they are forced to release publicly to get marketing to get others to pay based on hype.
Wow, Cloudflare is definitely buying some goodwill from me. Just consistently interesting new releases alongside and solid products at great prices.
Seems nearly too good to be true.
I’d love to see someone build a model of this sort that can actually accept priors and do something intelligent with them.
[0] You can feed Jev a prior as text. I’ve tried it. It works poorly.
And it's only been a few weeks.
There are many, many of those left around, because AI frontier is moving forward so fast, everyone is racing ahead. Which is why I laugh when people say AI is not transformative and LLMs are a dead end (and my favorite, "what are we going to do with all those GPUs when the bubble pops?"). Even if SOTA LLMs hit a hard capability limit tomorrow and never advanced again, there's a good decade of growth and advancement to be extracted just from all the low-hanging fruits that were left unpicked along the way.
Diffusion transformers are not "easy" but underfunded.
Random one in terms of applications: getting GPT-4-level[0] LLMs to operate at hundreds of tokens per second on edge hardware - opens up so many possibilities I'm probably unable to imagine half of them.
E.g. Imagine spellcheck/predictive text (or code autocomplete) where the model is able to process a whole paragraph + surrounding application/system context in between keystrokes. Or an OS being able to reliably guess what you're doing in real-time, in between your UI interactions, and offer actually helpful contextual reactions.
Or imagine finally funding some decent studies into exploring the models as computational artifacts - studying their latent spaces, how they form and how they model reality internally.
Or imagine automated sliding doors that don't suck.
--
[0] - Or anything substantially better than BERT-level models used in Jev or that demo from the company doing inference ASICs, that has a chatbot online that does 14 kilotokens per second.
But also harnesses and more generally new insights on "the control flow problem" could end up squeezing a ton of performance out of small models.
Enough stuff can happen, software use itself might change, and that could really cause anything. "What will we do with all the gpus" might become a question if for a magnitude of tech and reasons leaked-opus-9 runs on a macbook m6 or 7
That's low hanging for you?
This got everyone racing forward and right now there is not enough human attention left in the world to productionize this, or any of the other "side threads". When the race slows down, people will catch up, branch out, and loop back.
Assuming it won't get to full RSI, the current approach will burn out - most likely economically. The race slows down, people branch out, look back, start picking up the "untapped potential"/low-hanging fruits, and you have new S-curves launching in place of the one that just tapered off (hence a fallacy - a stack of S-curves adds up to continuing exponential growth).
In other words: it comes and goes. Hyperconcentrated capital will eventually deconcentrate.
[1]: "FPGA-based CNN Acceleration using Pattern-Aware Pruning" https://inria.hal.science/hal-04689673/document
We have overcome split brain problems before so this wont be our first
Of course you can also do ranking one-off with a decision model, but this likely less stable, and by doing pairwise ranking you can also relatively quickly do incremental inserts to the list.
The weights have permissive licensing, but the data and training pipeline are not published to reproduce them from their proprietary Qwen starting points. Weights are not "source."
<sad trombone sound>
Surely someone will soon do what the title of this post makes it seem like cloudfare did. Truly modular open source training and inference logic, along with a totally open corpus and weights, will eventually out-compete the closed ecosystem.
I bet the competition will result in research into how to make these decision models several more orders of magnitude faster and cheaper.
Here's a challenge problem - look at a 1M context window and produce N decisions (different queries) from it in 50-100ms.
16ms latency. And locally run.
https://at0m.pienomial.com/
Why go big when you can go small ?
There is no official qwen 3.8 9b
From the model card:
> Clef-Flash is post-trained from Qwen/Qwen3.5-9B. See Clef for the larger variant.
At0M: A 60M local Jev at 16 ms latency and 79% accuracy on Typed Decision
https://at0m.pienomial.com/ https://news.ycombinator.com/item?id=49920350
We wanted to stress test the system before the V1 release.
Businesses are built on outliers. It doesn't make sense throwing your hard earned insights while paying them money to steal it.
Also, cloudflare https://robindev.substack.com/p/cloudflare-took-down-our-web...
Or are companies/people already building this based on say an arXiv docs? n
---
The pricing is ... hm more expensive but not at the point I won't give it a try due to the embeded vision encoding
Now that we're hitting against the hardware supply limits of global economy, I expect more people to go back and revisit the things left along the way in the mad rush to "just throw more compute at it / make a bigger model" - and thus many more cases like Jev to show up in the next few years.
I've been playing with this for the last year or so. Started with a personal email classifier, also did benchmarks with some public datasets, then created a couple classifiers that could play Doom, and now I've been trying out some other experiments, like a request proxy/router to automatically choose a classifier and fallback to LLM to handle unseen requests
Jev did a great job at creating hype, but also at shaping the concept and space of "decision engine" or "decision model". People were already doing this with LLMs, which is very inefficient for most tasks like that, and the Jev guys figured there was a market there. It seems like they were right, and now there's a rush to flood the space, taking advantage of the hype window
In general, training a general purpose classifier is something lots of people have worked on for a long time. Large Transformer models themselves are typically "generalists" already, so structured generation and constrained decoding have given you the ability to use an LLM as a general classifier for years. It's an incredibly common pattern for working with LLM judges or any sort of branched decision making workflow.
A lot of people who are a bit less familiar with the field saw the hype around Jev and presumed that the reason it was so exciting was that it was a fundamentally new interface for working with an LLM. And that additional excitement drove even more attention to Jev. But fundamentally, TypeSafe's announcement was that they found a particular architecture/training paradigm that resulted in a model for this particular interface that had incredible accuracy, very low latency, and for which they could offer inference at a super low cost.
I've not kept up with the flood of Jev clones that have been released, but I think this is just typical for any new component in deep learning that gets popular. There are an absurd number of open source autoregressive LLMs and fine tunes you can use. The thing that makes one more popular than the other is typically the general performance of the individual model.
But training a model for this purpose, or emulating the procedures described in Jev's papers, isn't something that would be beyond the capabilities of any lab. It's not an entirely alien architecture or approach.
The bigger question for TypeSafe as a company would be if other teams are producing Jev-like models that win on performance or cost. Like I said, I haven't followed the reports super closely, so no idea if that's the case or not.
https://www.youtube.com/watch?v=AzxoU7kxjig
Latency won't be that good, but could still work similarly. Simply force the structured output of a LLM to the given schema.
Probably also easy to train because we can use stronget LLMs to generate input/output data, or even synthetic data is easy to generate.
It's not really a new technology, it's more like a new use-case.
https://github.com/blockbrain-ai/cygnet-recipe
The hard part is the data and evaluation. Sure, it’s not that hard to build a fast model with good predictive power. But fast at doing what? You probably don’t care about classifying whether a hotdog is a sandwich (which is the Jev demo).
At0M: A 60M local Jev at 16 ms latency and 79% accuracy on Typed Decision
https://at0m.pienomial.com/ https://news.ycombinator.com/item?id=49920350
I'd love an privacy first on-device model i could use in iOS.
At0M: A 60M local Jev at 16 ms latency and 79% accuracy on Typed Decision
https://at0m.pienomial.com/ https://news.ycombinator.com/item?id=49920350
I built this for my own needs, and thought others might find it useful too.
Perhaps that may be too costly atm
There are a few technical details that can reduce the latency significantly (covered in the post) but the real insight has been from watching the reaction to Jev and seeing that there's enough of a market interest to offer it as a distinct thing. The underlying concept/approach was already there.
The fascinating part to me is that Jev seems like this technique plus post-training to get multiple independent confidence values for each possible answer.
But, for these adhoc models, you need to understand the task more, collect some data and train the model (on CPU, no need for GPU). So Jev-like models are a great way of getting a hosted general decision model, but if you have a very narrow task or set of tasks, you might be better off with some more basic models that you can run on the same server you run other things or even on your laptop
Anyone can copy that and apply to an array of models - stripped down LLMs or already slim/highly performant traditional classification architectures (just wrap inference with an api that inputs/outputs the same structured data).
Jev, I think, would say their advantage is the intelligence of their models and training data including calibration: https://medium.com/code-applied/calibrated-classifiers-makin... (which i still struggle with in the general application... there's no free lunch with these things).
If you have a very narrow use case you can train a BERT based decision model on a laptop an hour if you have good data to train it on. It'll answer faster than the roundtrip to clef/jev and use <1gb memory
Many people seem to have run into the same question and started working out the answer.
It seems insanely obvious at least to me, that JEV is the new hot thing for the AI field since they give you stronger output that isn't... flat out wrong, that alone is impressive.
Getting training data that works well for calibrated classification objectives is difficult.
I hear conflicting opinions (including my own) about how well calibrated each of these are. Jev seems to be the best.
But the jev release made obvious the PMF for these models, and the underlying reality is that calibration really doesn't matter much when you're replacing usecases where people were using damn LM head softmax probabilities before, which are nowhere near calibrated.
So now everyone simply finetunes qwen and makes a compared-to-regular-LLM vastly cheaper decision model. And it works for majority of usecases. People mostly only care about accuracy, not confidence.
- Jev/TypeSafe: 230 ms median, 254 ms mean
- Jev/OpenRouter: 237 ms median, 267 ms mean
- Clef Flash: 661 ms median, 806 ms mean
What gives?
Instead, to make up for the lack of economic viability of their models, they are forced to release publicly to get marketing to get others to pay based on hype.