Has anyone actually seen better or the same results with Laya compared to Jev? From my experience, Laya performs significantly worse. It's less confident and often makes wrong decisions with more complex queries.
jonmagic 4 minutes ago [-]
I've been following jevbench twice a day for the past week and that's been a lot of fun. Latest update:
Rank System Score Public / sealed accuracy Evidence
Yes. JEV generalizes better because they probably have an enormous corpus and trained on it for a long time. Laya's out of the box model is much weaker. However, in the age of LLM's it's incredibly easy and cheap to generate large datasets to fine tune laya for your task, and the training loop is pretty quick and cheap too.
It's so easy that I question why I would ever pay for JEV when eventually I'll have done enough random things that I will also have a large corpus and likely a general model as well.
mtkd 9 minutes ago [-]
Isn't the point of Jev that it generalises better?
It's a fast classifier you can use out-the-box, ~1.5bn tokens is about $40 (I've been hammering it)
It just works ... a whole bunch of low-level/low-importance workflow stuff that was getting farmed out to small/fast LLM models now has a competitive alternative ... and bits that hadn't even been considered to go into some external descision/classifier service can be tested/deployed at ~$0.00003/req
I don't get this wall of negativity on it, it's genuinely innovative/useful tech ... would expect HN to be more positive, regardless of whether it's the absolute best execution
shepardrtc 4 minutes ago [-]
It really does just work. And it works so well I already integrated it into my product. Saves me about 75% of costs for the section its working in, which isn't a small amount. I see a lot of negativity and I don't really get it either. Its so cheap and so fast, why not give it a try?
cobanov 41 minutes ago [-]
Developer here. You're right, Laya is a lot weaker than Jev, especially on harder queries. It's a small model, so it's fast, but that's the trade-off. The open models that get close to Jev are much bigger, and running those is what I'm working on next.
mikodin 14 minutes ago [-]
What are the models? I am super curious in these as well
iamflimflam1 20 minutes ago [-]
Nothing yet. Unfortunately it sometimes feels like our industry has been overrun by grifters and chancers.
I’m sure this has been a gradual and long decline. Maybe it even started with the dot com boom and accelerated with crypto. With AI it seems to have got worse.
ranyume 51 minutes ago [-]
>Run decision models locally.
>example is a text classification task instead of a decision
hbrn 24 minutes ago [-]
"Decision model" is just marketing jargon.
decision model = classifier
system one model = small non-reasoning LLM
noul = boolean
confidence = f(probabilities)
It's sad to see how gullible engineers are today.
OgAstorga 32 minutes ago [-]
text classification is equivalente to decision. This is exactly the same thing Jev does.
ranyume 25 minutes ago [-]
If it has four legs, a tail and barks why not call it a dog?
gchamonlive 16 minutes ago [-]
Because this specific dog only barks in structured text
ricardobeat 25 minutes ago [-]
It is not. In a benchmark with actual decisions - navigation, traffic, waypoints - laya does slightly better than a small classifier, with very low correlation to state changes.
<<<"i was curious to see if i could train a competitive Jev-like model completely autonomously with a swarm of agents using our internal system."
Bro is writing off the H200 lol
On a sidenote I really can't stand the term "swarm" and definately plays into AI doomerism.
lirolero 17 minutes ago [-]
[dead]
cobanov 40 minutes ago [-]
The link rgbrgb posted is a good overview. The best open ones are close to Jev now, but they're big models. And I agree, if you have an eval set for a fixed task, a trained classifier is the better choice.
emmettbt 56 minutes ago [-]
Cool... but this does seem undermined by the fact that Ollama can add support for decision models at any time.
cobanov 39 minutes ago [-]
Fair, and I'd be happy if they did. Ollaya uses the same API as Jev, so your code isn't tied to it either way
accountrequired 38 minutes ago [-]
and that ollama is go-llama and not rust, so it's not really the ollama of anything
51 minutes ago [-]
handfuloflight 51 minutes ago [-]
Sounds good on latency but how is its actual decision quality vs. Jev?
cobanov 40 minutes ago [-]
Depends on the model. The small ones I support today are well below Jev on harder queries, but fine for simple, well-defined questions. The open models that get close to Jev are bigger, and I'm adding support for those next.
george_max 51 minutes ago [-]
I am fairly confident if Jev-style decision models are seen as prominent (which, they seem to be), Ollama will support them. Surprised the team hasn't implemented this already.
eserozvataf 52 minutes ago [-]
great project for empowering open-source alternatives.
rkovashikawa 41 minutes ago [-]
open-source is the only way for safe AI development. whoever doesn’t share the weights/code will lag behind.
cobanov 39 minutes ago [-]
Thanks!
Rendered at 19:46:37 GMT+0000 (Coordinated Universal Time) with Vercel.
Rank System Score Public / sealed accuracy Evidence
1 decider-4b v2 64.13 83.5% / 34.7% Evaluator-run, offline
2 Jev 1.13 63.29 86.6% / 36.7% Evaluator-run API
3 JevK5 v0.2 62.04 85.3% / 33.1% Evaluator-run
4 Cygnet 12B 61.76 87.9% / 33.8% Evaluator-run, offline
5 Hopper 59.43 82.3% / 34.1% Evaluator-run
28 Kev 4B 36.14 66.2% / 22.4% Evaluator-run
41 Laya 421M 30.25 58.4% / 30.8% Evaluator-run
It's so easy that I question why I would ever pay for JEV when eventually I'll have done enough random things that I will also have a large corpus and likely a general model as well.
It's a fast classifier you can use out-the-box, ~1.5bn tokens is about $40 (I've been hammering it)
It just works ... a whole bunch of low-level/low-importance workflow stuff that was getting farmed out to small/fast LLM models now has a competitive alternative ... and bits that hadn't even been considered to go into some external descision/classifier service can be tested/deployed at ~$0.00003/req
I don't get this wall of negativity on it, it's genuinely innovative/useful tech ... would expect HN to be more positive, regardless of whether it's the absolute best execution
I’m sure this has been a gradual and long decline. Maybe it even started with the dot com boom and accelerated with crypto. With AI it seems to have got worse.
>example is a text classification task instead of a decision
decision model = classifier
system one model = small non-reasoning LLM
noul = boolean
confidence = f(probabilities)
It's sad to see how gullible engineers are today.
Smarter move if you have an eval set is to just train a classifier and call it a day.
top open one is trained by perplexity cto for $3k, kinda cool https://x.com/denisyarats/status/2102252088067850507
Bro is writing off the H200 lol
On a sidenote I really can't stand the term "swarm" and definately plays into AI doomerism.