First, congrats to the team on launching something genuinely interesting and new.
Seems like a more accurate title would be "Jev: Trading general purpose generation for fast typed inference" or something like that.
This is interesting, but the speed comparison seems misleading? A generative model that can output code in a Turing-complete language can do anything a computer can do.
Jev can only generate structured output, right? This is probably super useful for classification/routing/scoring, but it's nothing like the code generating models we're all using today for code and automation.
Also "can't hallucinate" seems wrong? Sure, it can't emit an invalid type, but it can still emit a completely wrong valid value. You can enforce structured output from an LLM too, with an appropriate harness, etc.
Assuming there's no funny business, the Doom demo is cool.
I don’t think it’s misleading if you compare on the use cases they suggested. It’s faster and cheaper (no idea if higher quality), so it’s immediately interesting for certain things.
And if you buy their RLCD claims, this might be even better than huge models that know a bunch of irrelevant things.
"Jev: New frontier model 40-400x cheaper and 20-200x faster"
I'm not the gatekeeper of who gets to call themselves a frontier model, but I don't think most people would count Jev in that group. It sounds false.
If their specific claims hold up, then it would make more sense to say something like:
"Advanced the speed/cost frontier for structured decisions"
How is this not a frontier model? It's bleeding edge in its own niche. It's not a frontier LLM; however, applicable to many of the things people use LLMs for.
It's nothing like a traditional LLM and so should not be compared to one. It's a heavily constrained, tiny model that can only produce a probability score or a yes/no answer over pre-defined selections. It has no long-context capacity.
I mean, imagine comparing this thing to Astra, it's hilarious. They don't even tell you what the max input size is, and they only allow 10 possible answers to choose from for the Choice mode. It's probably like a 1billion param model. They say it's "not small", but there's zero reason to believe that.
I suspect someone will be able to recreate this within a week by piecing together open-weight models.
> It's nothing like a traditional LLM and so should not be compared to one.
Frontier LLMs are expensive jack of all trades. You can absolutely compare them to purpose-built tools on any domain they touch. Engineering is all about assessing tradeoffs.
Well, not quite a week: <a href="https://x.com/harshagundal/status/2100044305536889015" rel="nofollow">https://x.com/harshagundal/status/2100044305536889015 - apparently it took him 2 hours.
jacobgold · · focus · HN ↗
Seems like a more accurate title would be "Jev: Trading general purpose generation for fast typed inference" or something like that.
This is interesting, but the speed comparison seems misleading? A generative model that can output code in a Turing-complete language can do anything a computer can do.
Jev can only generate structured output, right? This is probably super useful for classification/routing/scoring, but it's nothing like the code generating models we're all using today for code and automation.
Also "can't hallucinate" seems wrong? Sure, it can't emit an invalid type, but it can still emit a completely wrong valid value. You can enforce structured output from an LLM too, with an appropriate harness, etc.
Assuming there's no funny business, the Doom demo is cool.
janalsncm · · focus · HN ↗
And if you buy their RLCD claims, this might be even better than huge models that know a bunch of irrelevant things.
WhitneyLand · · focus · HN ↗
"Jev: New frontier model 40-400x cheaper and 20-200x faster"
I'm not the gatekeeper of who gets to call themselves a frontier model, but I don't think most people would count Jev in that group. It sounds false.
If their specific claims hold up, then it would make more sense to say something like:
"Advanced the speed/cost frontier for structured decisions"
alfalfasprout · · focus · HN ↗
bigglebear · · focus · HN ↗
I mean, imagine comparing this thing to Astra, it's hilarious. They don't even tell you what the max input size is, and they only allow 10 possible answers to choose from for the Choice mode. It's probably like a 1billion param model. They say it's "not small", but there's zero reason to believe that.
I suspect someone will be able to recreate this within a week by piecing together open-weight models.
janalsncm · · focus · HN ↗
Frontier LLMs are expensive jack of all trades. You can absolutely compare them to purpose-built tools on any domain they touch. Engineering is all about assessing tradeoffs.
bigglebear · · focus · HN ↗