baobabKoodaa

Can we just ban Fortune and any other sources which trick the reader by giving the impression that the article is not paywalled, only to blur the text halfway through? The archive.ph link is not working either. We shouldn't have this type of deceptive moneygrabs advertised on HN.

In one of my client projects we've had to do forced upgrades of LLM models because of deprecations (I believe three or four of them over the course of 2 years). Each time our internal benchmarks have shown REDUCED performance after upgrading to "better" models.

You don't seem to understand what the point of Jev is when you say "you can fine tune it for your use case". Building your own classifiers for your specific business problems is the type of work we all used to do back in 2016 or so. It costs very much. Jev is a cheap and fast general purpose classifier.

If you have an easy problem that can be solved by a classifier from pre LLM era, then sure, go ahead. But we have LLMs now and we can use those to expensively and slowly classify harder problems using general purpose models, without needing to spend a huge amount of time fine tuning a model for the specific task. Jev offers to do the same fast and cheap.

For clarity: no, a 0.8B model is not gonna do that.

The claim in OP is that "ASML currently sells no chipmaking machines in Europe". A single chipmaking machine purchase into a fab in Europe would be enough to prove that claim wrong. The number of fabs in Taiwan is irrelevant to this claim.

Is there any particular area of employment for algo geeks that you would approve of? Maybe we should just live off unemployment benefits instead of working?

I've seen enough proof to convince myself, but unfortunately I don't have enough to convince you. Maybe others will publish proper evals.

Yes, all of those are using small models (not this particular model, but small models nonetheless). Small models are not frontier intelligence.

Don't cut the quote mid-sentence. Here's the full quote:

> note: this is a parody blog post, see these links for better/more complete open implementations of Jev: OpenJev, openjev-sglang, and OpenJev on DiffusionGemma.

Is Jev built on top of 8-bit quantized 0.6B param Qwen model? No.

Fast and accurate general purpose classifiers DID NOT EXIST before Jev. You could either use an LLM to get a slow and accurate general purpose classifier, or you could use a smaller model to get a fast and inaccurate general purpose classifier, or you could fine tune your own model that would be both fast and accurate, but it wouldn't be general purpose.

Except in this case it's not technically correct. Jev's claim is that it's frontier intelligence and these guys are pretending that a 8-bit quantized 0.6B param Qwen model is that. There's no universe in which that claim is technically correct.

Yeah it says it's a parody, but then in the same sentence it refers to the other "OpenJev" implementations, which are basically the same thing with marginally more effort. And it doesn't imply that those things are parodies too (and I don't think they are parodies).

Somehow the HN crowd has a bunch of "professionals" who don't care about error rates and think that a Qwen model running on a potato is frontier intelligence.

I'm so sick of seeing these people who "made Jev in 25 lines of Python" or whatever the flavor of the day is. Do you people seriously think that Qwen3-0.6B-Q8_0.gguf is frontier intelligence? If you want to argue that Jev is NOT frontier intelligence, then go make that argument. Don't try to pretend that Qwen3-0.6B-Q8_0.gguf is frontier intelligence. That's retarded.

You might be right. I don't know. But regardless if Jev is frontier intelligence or not, Laya most definitely is NOT.

The point is that it's silly that the law is specific to onions, and the explanation "it's because onion market was small enough to be cornered" is unsatisfactory because there are other small markets too

There are many other small markets as well, and yet, this law is not called the "Don't Corner Small Markets Act".

Jev claims to be frontier intelligence. Laya, while claiming to be "the open source version of Jev", is using a tiny open weight model with a tiny context window. Anyone who has experimented with tiny models knows that they are far from "frontier intelligence". It's not plausible that Laya could be "the open source version of Jev", with "frontier intelligence", when it is using these tiny models.

Also, the paper that OP is referring, is not describing anything that sounds like a generalist classifier (which is what Jev is). Their paper describes a tailored solution to one specific business problem. I'm sure it has some similarities with Jev, but it's still a completely different thing, and I'm confused why OP is claiming it to be the same thing.

If you don't believe me, just open the PDF and read the abstract.

If you need a reasoning model, then that is a System 2 decision, not a System 1 decision. This thread is about "Laya", a "Jev" competitor/precursor, which is a System 1 thing.

So you're not even trying to defend your claim? Reminder, you said:

> I had used versions of bert to achieve the same functionality years ago

I remember when BERT came out. I played with it. Other people played with it. You couldn't really get it to do useful stuff, unless you put a ton of effort into it, and even then, it would BARELY do anything useful.

The promise of Jev is that it's FRONTIER INTELLIGENCE, not the intelligence of a pre-chatGPT era model.

If you are trying to claim that BERT is somehow on par with frontier models, that is laughably false. (Whether Jev is on par with frontier models can be questioned as well.)

> output text

according to the people who made Jev, it does NOT output text. it's a closed model, so we can't inspect the internals, but i would just take their word for it.

just because the API responds with JSON text, does not mean that the underlying model is generating JSON text.

it's an AI generated webpage that uses small LLM models to produce structured output. it has nothing to do with jev.

In the link of the comment I was responding to, they explicitly say that Jev is not LLM-based:

> Is Jev just a smaller LLM?

> Jev is neither small nor an LLM, hence being off the intelligence Pareto curve.

Why is this slop getting 200+ points on HN? This should be flagged to oblivion. This has no relation to Jev, other than that it makes fun of Jev and tries to confuse users what this is and what Jev is.

It's a closed model and they claim that it's not LLM-based, so I'm not sure why you are claiming that it is LLM-based.

Anyone who believes this news story should create their LLM slop bot to trade on prediction markets like Polymarket and Kalshi. These acceletards provide a great influx of money to many human traders on these platforms.

You people just never stop, do you? At some point you're gonna have to look back at all the times you said "LLMs have hit a wall" and look at what the progress was since the last time you said that. Please do go ahead and revisit your comment here 1 year later. Embarrassing.

Your link is from 2013. You're intentionally using the term "Agent" to muddy the waters. Don't do that.

No. You don't "defet" (sic) "incorret" (sic) arguments by making up new definitions for existing words. Stop doing that.

the first "sentence" just seems to continue indefinitely into word salad