Rendered at 17:26:07 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
hbrn 19 hours ago [-]
$40m in funding, 2 years in stealth.
Performs on-par with SemIf which was built in a couple days and apparently uses raw Qwen, with no fine-tuning. SemIf runs in your freaking browser. Oh and Jev is twice as expensive?
Is it surprising that Jev consistently thinks it's Qwen?
I'm almost convinced that Jev is a scam. Take Qwen, fine tune it a little, tell investors it cost $10m, spend $1m on advertising, profit.
vessenes 6 hours ago [-]
I think it’s much more likely that these benchmarks are not good, in that they do not explore much of the space that jev was (likely) trained to cover. The doom demo is a good example — I’d like to see a wide variety of things like that included in any benchmark, not just ‘email classification’ or what have you.
Think of it this way: there’s some time needed to optimize / design an architecture, and the world gets that for free when it’s described. As to the rest of the last two years spent, is it more likely a former oAI lead spent them fucking around, or adding as many RL environments as possible to its model that is supposed to be a generalized classifier?
Right now my prior is that jev is probably better than these rando weekend models, whether or not we know how to test and demonstrate that in a benchmark. It’s also super cheap, so I don’t think there’s a strong reason not to try out building with it first, then walk down the ladder to an open model if you need to for some reason.
hbrn 4 hours ago [-]
So if benchmark says Jev sucks, it's benchmark's fault. And yet Typesafe doesn't share anything about their internal benchmark that apparently proves how amazing Jev is.
Funny enough, when I tell people that Jev cannot play tic-tac-toe I hear a similar argument - it's not what Jev was built for. Jev has this elusive use case that noone can describe, so when Jev fails, it's just because it wasn't built for it. Convenient.
Don't you find it suspicious that Jev cannot play tic-tac-toe or checkers, but can play Doom? Don't you find it suspicious that nothing of the Doom demo was shared: no harness, no control loop, no state encoding, no prompts - nothing.
And the explanation is obvious - Jev isn't playing doom. The harness is. They essentially built a Doom bot, dumbed down it's control loop for Jev, and gave reins to Jev. Look mom, Jev is playing Doom!
The state says "you're pointing at the cacodemon" or "you're not pointing at the cacodemon" and Jev has to decide whether to press fire. Frontier intelligence!
You can build a harness where a coin flip is playing Doom.
florianstandhar 6 hours ago [-]
[dead]
Retro_Dev 18 hours ago [-]
Isn't the entire deal with jev that it is fast? I'd be interested to know how the energy cost of the Qwen-based model compares with Jev. Of course, Jev is currently locked up so we don't know... "Trust me bro Jev is revolutionary and amazing, pay more money for our inferior product which costs more to run, and of which you need to access by sending us the data"
dmix 17 hours ago [-]
You can spot vibecoded websites by how they include the prompt or commit-style comments into the literal interface, instead of communicating it via visual context (or simply excluding it)
> Sort by any column; values the run could not produce always sort last. Hover a cost for how it was priced, a latency for the endpoint. Names link to each project.
A designer would never write this, but an LLM just inserts it by making it small grey text next to the interface, just like it does with inane code comments.
spiderfarmer 11 hours ago [-]
EYEBROWS EVERYWHERE
There are lots of tells in every vibe coded design.
anukin 14 hours ago [-]
And why is a designer needed for every website in the world?
wannabe44 7 hours ago [-]
I (not GP) have no issues with CSS part of the design (just as I am fine with bootstrap websites). But if you can't be arsed to write 4 lines of text describing it in human language instead of the claude vomit, you probably didn't put much effort to begin with.
spiderfarmer 10 hours ago [-]
They're not needed. And there are bad designers everywhere.
And I know HN people think marketing is a bad word.
But marketeers know that design is part of the messaging. And nowadays, having clear AI tells in your design shouts "I made this in an afternoon, so don't take this seriously"
First impressions are everything in a world where attention spans are shortened every year.
Act accordingly.
dogscatstrees 16 hours ago [-]
It's helpful metadata, what's wrong with it? Dashboards at work do this.
janalsncm 15 hours ago [-]
One person’s helpful metadata is another person’s noise. It’s much better for a door to visually indicate that it should be pushed open than to put up a sign there.
However, doing the former requires a level of empathy with humans that LLMs rarely have.
Human brains have caloric demands. It is possible for humans to process enormous amounts of unrelated facts to make a decision, but it’s tiring. It’s much better to not do that, especially just to get some basic information.
To anthropomorphize a bit, an LLM might find it charming and interesting to read someone’s life story as a preamble before their taco recipe. Humans by and large find that annoying, not because we can’t understand the biography but because processing that information is not free.
So it’s probably possible to design using an LLM. You would probably have to be intentional about it.
dmix 15 hours ago [-]
Well said
Much has been discussed about AI coding but there's been a lack of discussion on the design/UX side as that's also a step being rushed by via prompting + "looks pretty enough".
We're entering an era of hyper dense UIs with plenty of excess and quick workarounds.
CBLT 16 hours ago [-]
If you don't have any kind of agent instructions saying "don't copy code into prose", you'll inevitably get text that reflects some previous state of the system instead of its current state.
dmix 16 hours ago [-]
It's fine in isolation to have help text for complex interfaces needing explanation. Better yet contextual hints.
But there's about 10 other examples explaining intention of the coding rather than immediately useful information to the user, it's all over this one site in small grey text. And I guarantee you nobody is reading them carefully. Just like how nobody likes reading a 15 line LLM code comment over a simple function.
Most of it could be better solved with more thoughtful design or deleted. The link explanation is particularly egregious.
"instructions": "Which intent does the user's message express?",
"labels":["set_alarm", "play_music", "weather", "send_message", "turn_off_lights"],
"state": "Play some Taylor Swift.",
"expected": "play_music"
Happy to — please open an issue at https://github.com/fstandhartinger/jevbench/issues with an endpoint or runnable code, the model and licence, and whether it was trained on the public items. Every entrant runs through the same harness, including the sealed set.
I definitely prefer open models I can run locally, because sending our private held-out set of tasks to an external API produces some headaches on ur side and basically means we have to rotate the test set a lot, to avoid contaimination.
We can call API hosted models though, we'll just flag the leaderboard entries appropriately.
Many SaaS vendors forbid benchmarking, I find it crazy that such anti-competitive terms are standard across the industry but they are. Generally the goal of such terms is to "control the narrative" around the product, regardless of the truth of performance being better or worse than competitors.
meander_water 10 hours ago [-]
They released some examples of what their workflow evals are like. I'm sure you could reverse engineer a benchmark from that
Interesting; was curious how this didn't fall into trouble with ToS. Apparently the "no benchmarks" clause was intended for "limited preview" audiences and didn't get removed at launch on accident.
Maxious 8 hours ago [-]
But also no big deal because "I’m extremely anti-public benchmarks."
tomrod 19 hours ago [-]
I mean, that's a great reason to ignore JEV entirely.
"Trust, but verify" isn't just a catchy cliche. It's the only way to operate where models and code are fast to market.
florianstandhar 6 hours ago [-]
[flagged]
adityamishra241 11 hours ago [-]
How do you handle task distribution and prevent the benchmark from favoring models that are tuned specifically to these 534 questions?
florianstandhar 6 hours ago [-]
[dead]
17 hours ago [-]
janalsncm 15 hours ago [-]
It is strange that you put the BGE reranker in the list but not BART which is an actual zero shot classifier.
florianstandhar 6 hours ago [-]
Good call... BART-large-MNLI is the classic zero-shot baseline and it should be there. Adding it to the next run.
DylanMerigaud 11 hours ago [-]
534 English decisions in one full run sounds substantial.
MisterMunchkin 3 hours ago [-]
Lmao this just proves Jev is being shilled for money. Nobody would speak like this for fun.
Flagging AI written email is a much requested feature too.
542458 17 hours ago [-]
Keysmashing my keyboard resulted in 86% confidence that the text was AI written. I don't think this is a particularly good classifier, I've never seen an LLM output "kad jfkhasljkdhf laksjhdf".
Edit: If that's not realistic enough for you, the text "Hello world! My name is GravitasIsOverrated and I like coding and cooking. This text is 100% genuine, and not AI generated at all." results in 85% confidence that it's AI generated.
More broadly, I don't know why this would work. Qwen/Jev/whatever doesn't magically have the ability to discern AI-authored text from non-AI-authored text, and will increasingly get worse at it as the hallmarks of AI-written text change.
I asked free chatgpt to give me some essays that will fool a slop detector and they all fooled this slop detector. Its best guess was "6% slop probability 87% confidence answered in 0.5 s for $0.000027" and yet it was 100% slop.
I am very skeptical slop detectors will ever work.
pushpendraw 15 hours ago [-]
the slop detector giving 86% confidence on a keysmash is the real finding here, not the leaderboard score. confident and wrong is worse than an LLM that just hedges.
Performs on-par with SemIf which was built in a couple days and apparently uses raw Qwen, with no fine-tuning. SemIf runs in your freaking browser. Oh and Jev is twice as expensive?
Is it surprising that Jev consistently thinks it's Qwen?
I'm almost convinced that Jev is a scam. Take Qwen, fine tune it a little, tell investors it cost $10m, spend $1m on advertising, profit.
Think of it this way: there’s some time needed to optimize / design an architecture, and the world gets that for free when it’s described. As to the rest of the last two years spent, is it more likely a former oAI lead spent them fucking around, or adding as many RL environments as possible to its model that is supposed to be a generalized classifier?
Right now my prior is that jev is probably better than these rando weekend models, whether or not we know how to test and demonstrate that in a benchmark. It’s also super cheap, so I don’t think there’s a strong reason not to try out building with it first, then walk down the ladder to an open model if you need to for some reason.
Funny enough, when I tell people that Jev cannot play tic-tac-toe I hear a similar argument - it's not what Jev was built for. Jev has this elusive use case that noone can describe, so when Jev fails, it's just because it wasn't built for it. Convenient.
Don't you find it suspicious that Jev cannot play tic-tac-toe or checkers, but can play Doom? Don't you find it suspicious that nothing of the Doom demo was shared: no harness, no control loop, no state encoding, no prompts - nothing.
And the explanation is obvious - Jev isn't playing doom. The harness is. They essentially built a Doom bot, dumbed down it's control loop for Jev, and gave reins to Jev. Look mom, Jev is playing Doom!
The state says "you're pointing at the cacodemon" or "you're not pointing at the cacodemon" and Jev has to decide whether to press fire. Frontier intelligence!
You can build a harness where a coin flip is playing Doom.
> Sort by any column; values the run could not produce always sort last. Hover a cost for how it was priced, a latency for the endpoint. Names link to each project.
A designer would never write this, but an LLM just inserts it by making it small grey text next to the interface, just like it does with inane code comments.
There are lots of tells in every vibe coded design.
And I know HN people think marketing is a bad word.
But marketeers know that design is part of the messaging. And nowadays, having clear AI tells in your design shouts "I made this in an afternoon, so don't take this seriously"
First impressions are everything in a world where attention spans are shortened every year.
Act accordingly.
However, doing the former requires a level of empathy with humans that LLMs rarely have.
Human brains have caloric demands. It is possible for humans to process enormous amounts of unrelated facts to make a decision, but it’s tiring. It’s much better to not do that, especially just to get some basic information.
To anthropomorphize a bit, an LLM might find it charming and interesting to read someone’s life story as a preamble before their taco recipe. Humans by and large find that annoying, not because we can’t understand the biography but because processing that information is not free.
So it’s probably possible to design using an LLM. You would probably have to be intentional about it.
Much has been discussed about AI coding but there's been a lack of discussion on the design/UX side as that's also a step being rushed by via prompting + "looks pretty enough".
We're entering an era of hyper dense UIs with plenty of excess and quick workarounds.
But there's about 10 other examples explaining intention of the coding rather than immediately useful information to the user, it's all over this one site in small grey text. And I guarantee you nobody is reading them carefully. Just like how nobody likes reading a 15 line LLM code comment over a simple function.
Most of it could be better solved with more thoughtful design or deleted. The link explanation is particularly egregious.
e.g.,
https://evals.typesafe.ai/
"Trust, but verify" isn't just a catchy cliche. It's the only way to operate where models and code are fast to market.
We've been experimenting with Jev for classifying email, some thoughts here: https://housecat.com/blog/classifying-email
Flagging AI written email is a much requested feature too.
Edit: If that's not realistic enough for you, the text "Hello world! My name is GravitasIsOverrated and I like coding and cooking. This text is 100% genuine, and not AI generated at all." results in 85% confidence that it's AI generated.
More broadly, I don't know why this would work. Qwen/Jev/whatever doesn't magically have the ability to discern AI-authored text from non-AI-authored text, and will increasingly get worse at it as the hallmarks of AI-written text change.
I am very skeptical slop detectors will ever work.