Rendered at 20:13:38 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
alex7o 2 minutes ago [-]
Guys I have a real q, what is the difference between an instruct based re-ranker and laya/jev I just don't see it.
george_max 1 hours ago [-]
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 31 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 36 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
digitaltrees 8 minutes ago [-]
I think your point is valid but many are annoyed that it is presented as groundbreaking, revolutionary, novel frontier tech when it is a known classification system. It’s the hype that feels undeserved. Honestly it was one of the best marketing campaigns I’ve seen.
shepardrtc 31 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?
not_a_bot_4sho 22 minutes ago [-]
I didn't see any negativity in the post you replied to.
I think the point being made is that Jev is great but it has no competitive moat, and open source versions will very soon catch up if their secret sauce is just synthetic data.
(Whether or not that is true, I don't know.)
cobanov 1 hours 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 41 minutes ago [-]
What are the models? I am super curious in these as well
verdverm 7 minutes ago [-]
one day, perhaps people will click through to the laya author's arxiv paper content and the why may become clearer, you won't have to read it, a skim will suffice
iamflimflam1 47 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 1 hours ago [-]
>Run decision models locally.
>example is a text classification task instead of a decision
hbrn 51 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 59 minutes ago [-]
text classification is equivalente to decision. This is exactly the same thing Jev does.
ranyume 52 minutes ago [-]
If it has four legs, a tail and barks why not call it a dog?
gchamonlive 43 minutes ago [-]
Because this specific dog only barks in structured text
ricardobeat 52 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.
Their marketing language is misleading. They must still use some transformer language model backbone to encode the text input (BERT or decoder-only LLM). The biggest difference is the output, instead of auto-regressively generating tokens, they produce probabilities over a bounded set of decisions (more flexible classification).
cobanov 1 hours ago [-]
Fair point, that example is basically classification. I'll change it to something that looks more like a real decision.
mococa 39 minutes ago [-]
It would be really cool to have LLMs and System One in a single tool - in this case, if Ollama implemented it.
datadrivenangel 1 hours ago [-]
Are there many models that are comparable to Jev for generic decision making?
Smarter move if you have an eval set is to just train a classifier and call it a day.
<<<"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 44 minutes ago [-]
[dead]
cobanov 1 hours 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 1 hours ago [-]
Cool... but this does seem undermined by the fact that Ollama can add support for decision models at any time.
cobanov 1 hours 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
1 hours ago [-]
accountrequired 1 hours ago [-]
and that ollama is go-llama and not rust, so it's not really the ollama of anything
gauravsapkotanp 26 minutes ago [-]
I have also tried this and its really awesome
handfuloflight 1 hours ago [-]
Sounds good on latency but how is its actual decision quality vs. Jev?
cobanov 1 hours 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 1 hours 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 1 hours ago [-]
great project for empowering open-source alternatives.
rkovashikawa 1 hours ago [-]
open-source is the only way for safe AI development. whoever doesn’t share the weights/code will lag behind.
cobanov 1 hours ago [-]
Thanks!
imnotr0b0t 19 minutes ago [-]
[dead]
adityamwagh 9 minutes ago [-]
Hey Claude, make ollama for Jev like models. Make no mistakes /s
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
https://benchmarkheaven.com/jev-models
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 think the point being made is that Jev is great but it has no competitive moat, and open source versions will very soon catch up if their secret sauce is just synthetic data.
(Whether or not that is true, I don't know.)
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.
(already merged)