Did Jev take off briefly and stopped getting talked about a few days later? Yes.
But that doesn't make it a failure. In the era where we have:
a) an AI hype cycle where the benchmark of "successful product" is ChatGPT, Claude Code, etc.
b) a social media environment that only rewards the most-engaged content
It's easy to declare something "fell off" because it didn't immediately revolutionize how everyone does their daily work.
But by that measure, nearly everything is a failure, even if it creates great businesses. That's especially true for infrastructure that runs in the background.
The author ironically thinks people talking about a product is more indicative of its success than its success – which is hype, the very thing he railed against.
Likewise, I switched over about 20 frustratingly buggy llm judgement calls that were using Luna (should the model use X tool, should it trigger deep research, what topic is the question etc.). I had spent days tuning the prompts to get somewhat decent results - meaning correct maybe 70% of the time.
I told an agent to test switching those all over to Jev. Came back a couple of hours later, thinking of this as an experiment, no major expectations, to find that they were all giving 100% accurate results in 800ms median time.
So it got adopted in a couple of hours work, it's live now, working very well, and I haven't had to think about it for the past week. That's the definition of a successful product.
EDIT: I should note two things
- there was actually one non English case that didn't have such high accuracy, now that I think about it.
- I assume a big part of why I got such good results was that I'd already spent ages tuning the prompts for Luna
OpenAI has a decisions API now so you didn't even have to migrate to Jev at all. Personally I'm using the open weight D3 decision models which work great and work locally on everything from phones to beefier computers due to the range of models they have.
It's still a pretty new field but Jev handily beats Luna-decisions on the Artificial Analysis Decision Index on every metric (price, latency, and accuracy)
I already have openrouter wired in so it was about as easy either way. Anyway I'm always happy to switch even a little bit of the stack away from OpenAI.
E every 2 weeks we have a new hype cycle so all in according to how stuff already works I don't see something special here. I use jev, but it does not solve all my problems.
They literally raised $870 million this month. It's like people think the hype cycle = success of business for some reason. I'm sure a couple of months later, they're going to release something new, hire a lot of PR, and the same people will be "man, Jev had fallen but this new [xyz] brings them so back! [xyz] industry will now be dead!"
After reading the article I can see that the comments here are a bit off. For example see this quote from the article:
> It’s not dead. Some companies use it while I believe the majority of use cases are addressed by open-weight rivals.
The point the article is making is the incredible way Jev specifically caused insane hysteria and hype, and just as suddently faded away. Not that it's dead or that the concept is severely flawed.
I think Jev is a good example of how great marketing fizzed out in the face of reality.
Is it useful? Yes.
Is it relevant? Yes.
Is it dead? Just its hype.
Is it revolutionary? Depends on your cost, quality, speed triangle.
Is it as big as it was claimed? I hope you have the answer by now.
contrary to what i feel is extreme negativity of the author, to me it seems Jev is one of the only novel releases that lived up to the hype and has staying power. Not only that it jump started a whole new "classifier" war, leading to now things like cloudflare's clairic for extraction.
We use it in production. Tested a bunch of alternatives (openai decision api, llm based approaches) and they are either too slow or not as good. But mostly too slow.
HN has a funny was of bubbling up low value article such as this.
Jev is far from being a fallen software. It works and it works well. Just because no one is talking about it does not make it a failure.
We reached inverse hype: where the folks jaded by hype are so jaded that they start to hype the same low value content they normally deride... as long as it speaks counter to any hyped topic.
Ironically, that technique usually pans out since a lot of useless fads get hyped. But every once in a while it causes people to completely and utterly miss the point.
I call it “SchadenFraud”: reveling in and playing up every little negative thing that happens in the AI world to make it look like it’s all just hype and will come crashing down any moment now.
At one point the hype truly was overwhelming (maybe it only appears less so these days because a lot of it seems justified now) and needed some counterbalance, but this is not it. We need balanced expert perspectives grounded in evidence.
Instead we get get TFA and other similar content from the usual suspects (you know who they are) largely because they’re building their careers on very loudly telling people what they want to hear, which may not be what they need to hear.
This is not harmless, because it gives folks the hope that things have not irrevocably changed and will soon go back to normal after the bubble pops. Personally, I’d rather get a stark but realistic picture of what’s happening now so I can prepare better for the future.
Typesafe over-hyped their useful product and successfully got it in front of AI devs. So to be assholingly snarkily reductive I can sum this up as
"founder did founder shit well"
Jev feels like what happens when people that have had no serious statistics get a glimpse of what statistics makes possible. I'm not talking about the developers of Jev, I'm talking about the uninformed that went all hype cycle on it. It's well designed and the advanced system a good statistical programmer would write.
>I think Jev is a good example of how great marketing fizzed out in the face of reality.
My read on Jev was totally different, I guess.
I first heard about it here. I found a video demo and thought it looked amazing, I saw a lot of discussion about it because other people probably also thought it looked amazing and imagined the possibilities, and then things quiet down because real-world use-cases for it are going to not happen right away, and definitionally it seems like Jev is more about supporting other stuff than being the thing itself.
All the other stuff about ambiguity and jargon and drama don't really register to me, I dunno. But it was interesting to see the author's take on that stuff, I suppose!
I think there seems to be extremes in both ends and in my opinion neither of these extremes are the ICP. If you're using AI to finish your work, you're not the ICP. If you're building a product and want to implement AI in your product, you're the ICP.
FinnLobsien 1 day ago
But that doesn't make it a failure. In the era where we have:
a) an AI hype cycle where the benchmark of "successful product" is ChatGPT, Claude Code, etc. b) a social media environment that only rewards the most-engaged content
It's easy to declare something "fell off" because it didn't immediately revolutionize how everyone does their daily work.
But by that measure, nearly everything is a failure, even if it creates great businesses. That's especially true for infrastructure that runs in the background.
ordinaryradical 1 day ago
The author ironically thinks people talking about a product is more indicative of its success than its success – which is hype, the very thing he railed against.
JKCalhoun 1 day ago
(They may be right.)
nameless912 1 day ago
esperent 1 day ago
I told an agent to test switching those all over to Jev. Came back a couple of hours later, thinking of this as an experiment, no major expectations, to find that they were all giving 100% accurate results in 800ms median time.
So it got adopted in a couple of hours work, it's live now, working very well, and I haven't had to think about it for the past week. That's the definition of a successful product.
EDIT: I should note two things
- there was actually one non English case that didn't have such high accuracy, now that I think about it.
- I assume a big part of why I got such good results was that I'd already spent ages tuning the prompts for Luna
satvikpendem 1 day ago
pants2 1 day ago
esperent 1 day ago
alex7o 1 day ago
Semaphor 1 day ago
altmanaltman 1 day ago
Harukadia 1 day ago
andyferris 1 day ago
zer00eyz 1 day ago
No one was talking about PHP last week either. Till we all got a reminder that a massive chunk of the web is still happily running on it.
Being talked about is a terrible metric for anything other than how much people are talking about something.
cyanydeez 1 day ago
Daviey 1 day ago
armcat 1 day ago
> It’s not dead. Some companies use it while I believe the majority of use cases are addressed by open-weight rivals.
The point the article is making is the incredible way Jev specifically caused insane hysteria and hype, and just as suddently faded away. Not that it's dead or that the concept is severely flawed.
vitorfblima 1 day ago
senordevnyc 1 day ago
owebmaster 1 day ago
alexey-salmin 1 day ago
danr4 1 day ago
really early to call it "the fall of jev"
eknkc 1 day ago
gonzalohm 1 day ago
owebmaster 1 day ago
therealalexz 1 day ago
yitchelle 1 day ago
BoorishBears 1 day ago
Ironically, that technique usually pans out since a lot of useless fads get hyped. But every once in a while it causes people to completely and utterly miss the point.
keeda 1 day ago
At one point the hype truly was overwhelming (maybe it only appears less so these days because a lot of it seems justified now) and needed some counterbalance, but this is not it. We need balanced expert perspectives grounded in evidence.
Instead we get get TFA and other similar content from the usual suspects (you know who they are) largely because they’re building their careers on very loudly telling people what they want to hear, which may not be what they need to hear.
This is not harmless, because it gives folks the hope that things have not irrevocably changed and will soon go back to normal after the bubble pops. Personally, I’d rather get a stark but realistic picture of what’s happening now so I can prepare better for the future.
david_shi 1 day ago
leemoore 1 day ago
hanifbbz 1 day ago
owebmaster 1 day ago
4r73m190r0s 1 day ago
pmdr 1 day ago
bsenftner 1 day ago
Brendinooo 1 day ago
My read on Jev was totally different, I guess.
I first heard about it here. I found a video demo and thought it looked amazing, I saw a lot of discussion about it because other people probably also thought it looked amazing and imagined the possibilities, and then things quiet down because real-world use-cases for it are going to not happen right away, and definitionally it seems like Jev is more about supporting other stuff than being the thing itself.
All the other stuff about ambiguity and jargon and drama don't really register to me, I dunno. But it was interesting to see the author's take on that stuff, I suppose!
freecodeio 1 day ago
wateralien 1 day ago
handzhiev 1 day ago