Jev AI Just Dropped, And.…

Author: Jack Roberts · Watch on YouTube

Video authored by the channel shown, not by IANIA; all rights belong to the creator. Transcript and summary generated automatically; the original-language content is preserved.

Original language: English

Original video: Jev AI Just Dropped, And.… · Channel: Jack Roberts · 11:23 · Watch on YouTube

Topics: AI agents, Task and workflow automation, Model inference and optimization, AI models

Summary

The video presents “Jev” as a fast, low-cost model designed for structured decisions rather than open-ended conversation. The presenter demonstrates using it for spam filtering, email ownership and urgency, churn-risk scoring, support-ticket routing, AI-slop detection, design matching, and selecting which model should handle a task. The suggested approach is to pair Jev with larger models such as Astra: Jev handles quick, quantifiable decisions, while the larger model handles more complex work. The presenter emphasizes that Jev is not a frontier-level chat model and is most useful when a task can be reduced to a yes/no answer, an option, or a score.

Key points

Jev is described as optimized for fast, inexpensive microdecisions, not for generating conversational language.
The three decision formats highlighted are yes/no, choosing from predefined options, and assigning a score or ranking.
The presenter compares Jev with Astra on email tasks, reporting that Jev was faster and cheaper in the examples shown.
Possible workflow uses include spam filtering, assigning email ownership, identifying urgency, and detecting buying signals.
The video demonstrates scoring customer churn risk and routing support requests to the appropriate queue.
Jev is shown being used to classify posts as AI-generated or “slop,” including filtering content from social feeds.
The presenter also uses Jev to identify matching designs from a library and to route queries to different models.
The recommended setup combines Jev with a larger model: use Jev for simple, quantifiable decisions and a stronger model for complex reasoning.
The presenter says Jev is accessible through OpenRouter and frames its usefulness around speed and cost rather than frontier-level intelligence.

Chapters

Start	Chapter	Summary
00:00	What Jev is and how it makes decisions	The presenter introduces Jev as a fast, inexpensive model and describes its yes/no, option-selection, and scoring outputs.
02:03	Email filtering and workflow examples	The video compares Jev and Astra on email classification, then shows examples such as ownership, urgency, and customer-risk scoring.
05:41	AI-slop detection and design classification	The presenter demonstrates using Jev to detect AI-written content and find suitable designs from a large reference library.
09:18	Routing tasks to the right model	The video shows Jev selecting models for different tasks and explains how it can act as a decision-making tool alongside Astra.
10:52	When to use Jev	The presenter says Jev is best for quantifiable yes/no, option, or scoring decisions, while noting that speed and price are not the same as capability.

Quotes

It’s a fundamentally different way of thinking about AI. — 01:01

Speed and cost. And the reason why it works this way is because Astra and other models like it, like anything else, like Claude, have been designed to give you words. — 05:41

It’s not Frontier level, but we’re not using it for that. — 10:52

If you can actually reduce anything down to a series of decisions, and you can quantify those decisions, you can accomplish some pretty spectacular things. — 11:23

Concepts and entities

Jev, GPT-6 Astra, Claude Fable 5.1, OpenRouter, Type Set, Slop Monster, Agenty OS, Jack Roberts

Full transcript (original language)

00:00 Jeff just dropped, and it is the world’s fastest model and 400 times cheaper than GPT-6 Astra. It is a fundamentally different type of AI that you need to understand. And we’re going to cover exactly what it is and five incredibly powerful use cases that you can use today to get light-years ahead, even if you’re completely beginner. And also, when you definitely shouldn’t use it. Now, first thing to understand is that it is significantly cheaper than the frontier models. I’ll show you what that looks like in a second throughout this video. Now, six reasons why we actually care about this. Number one, it gives

00:30 you unbelievably fast decisions. Of course, guys, grab the coffee. Very, very, very cheap, super important to bear in mind. Its outputs are 100% free. Yeah, exactly, 100% free. It can do parallel questions, so everything at the same time. It can actually also measure certainty, as well as give you a a very specific output. And also, it looks at typed answers. Now, to really understand how Jeff actually works, it was created by the fat one of the co-founders of ChatGPT, and they’ve been building in silence

01:01 with the doors locked and the windows closed for a couple of years, and then Jeff popped out. In a company called Type Set. It’s a fundamentally different way of thinking about AI. Obviously, we only care about what does it actually mean, and therefore, what changes. Now, essentially, it can give you an output in three different ways. It can give you a very simple yes, do it, no, don’t do it. It can give you a choice, so if you preload it with different things that it could choose from. And it can also give you a score, so a rank from one to 100 in many different ways. So, these are three ways that it can decide what to

01:32 do. But, the cool thing here is that when we combine it with GPT-6 Astra, with Claude Fable 5.1, and Jeff, by using some rules and a free skill output down below you can grab completely for free, it’ll be the second link in the description, we can effectively supercharge, get results way faster, that are going to be significantly cheaper. Now, with this, Jeff can do some crazy stuff. It can play games. It can play anything, cuz all it’s doing frame by frame is deciding of from these different buttons, WASD, which is where to move and also jump, what is the most optimum decision for me to make. So, you

02:03 can use Jev to do anything like this, like play games in real time. You can, for example, use it something like this where it’s lightning fast, where it can actually, based on many different classifying criteria, decide what the best image would be or what the best message would be. Now, on top of that, what else can you do? This is an internal link dealer and look at how fast it’s actually filtering it through. But, guys, I’m not here just to show you video games. I’m here to show you real-life use cases that are going to blow your mind. Now, let’s kick off with five levels. We’re going to go from inbox, community, slop. We’re going to do loads of really interesting stuff,

02:34 but let’s begin with level one. So, I pulled together a specific task. And what we’re going to do here is we’re going to have YouTube comments and we’re going to have a series of different tasks. I’m going to compare this with Astra to show you how this works. So, this is a spam and scam filter. So, effectively, what we do is connect Jev to, let’s say, it could be anything, right? It could be, for example, our Agenty operating system. Here, I can ask questions, power up, and see everything I want to. Or, I could just literally connect it to ChatGPT or Claude if I wanted to. Now, what I’m going to do here I’ve given it 20 different emails,

03:06 and some are scams and some are spam, and you’re going to see how quickly they’re identifying that. Going to run both models. We can see the time here. Look how fast Jev is going. That was completed in 3.41 seconds. Astra, it took, well, it’s still going to be fast. And I put the scores here so we can identify it. 9.93 seconds. So, it was three times faster. And if we look at the cost for Jev, that was about 1 cent. Okay, so it finished three times faster. And for Astra, that was significantly more expensive. I want to say about it, it’s 1 cent if you were to do this over

03:36 1,000 emails. And over 1,000 emails for Astra, you’re looking at just under $5. Let’s take a look at this one. This is ownership. Again, let’s run both models and see how it does that. This one is essentially saying go through my emails and identify who should own what. Again, Jev is just significantly faster and it has, once again a perfect score. It would have cost you 2 cents with Jev and 7 and 1/2 dollars with Astra. You get the idea. They’ve got ones for urgency, got ones can I identify them. Good buying signal. And look at how fast that is, guys. 2.57 seconds over 1,000 emails

04:09 that will cost you a cent. What can you buy with a cent? And again, Astra comes in at 10 seconds and 31. So, the point here is that we can actually now just connect and give Astra hands. So, essentially with the skill that I built, we just give it to Astra and effectively when that task could be done by Jev, we can do it significantly faster and at a way cheaper rate. Which takes us nicely onto level two. So, could it for example in a customer environment, could it identify, I don’t know, uh from a member post exactly how risky they are potentially churning based on what

04:40 they’re saying. So, say for example you have a CRM with your client and you want to give it loads of data, loads of different data and insights. It could actually calculate a score about how likely it is that an individual is going to leave, that employee is going to hand in a resignation, anything that you want to. So, this here is a churn risk. I’ve given it loads of stuff like, “Hey, I got my first automation ship.” This is a message. And it’s just going to quickly identify how likely it is. So, this is all fictitious stuff and again, it was done in 2.82 seconds and significantly cheaper. You can do the same thing with member intakes, with support routing,

05:11 anything that you want to. You can see effectively we’re getting the right ticket to the right queue. So, we have people dropping messages, asking questions. And let’s just say that we need to triage this and say, “Hey, great. Uh this is a billing question. This is an access question. This is a tech question.” We can use Jev and Astra together to go ahead and solve that. Same with intake forms, right? It’s cool. I want to build something useful. What’s their goal? Are they vague? Are they building? Do they want clients? And again, Jev can do that for you straight away. And again, the big time saver guys is speed and cost. That’s basically it.

05:41 Speed and cost. And the reason why it works this way is because Astra and other models like it, like anything else, like Claude, have been designed to give you words. Now, Jev doesn’t give you language like that. It’s not been optimized in that way, hence why it can do things in a completely different way. Now, level three is a completely different one. This is going to be the ability for it to identify AI slop. And by the way, if you’re wondering, Jev is accessible via OpenRouter. So, all we’re going to do is just ask what to do that. You give it your OpenRouter key, and it can call Jev effectively whenever you want to. That practically is how you’re

06:12 going to use it. Unless you’re doing something like this, where you have say an agentic operating system, and you’re asking questions, I can come down and have a conversation. And if you just come down, this is free, link down below. Just give this over to Astra or Claude, and effectively it tells you when you should bring in Jev, when not, and just give it your API key, and then you’ll be fully connected. So, let’s actually test its ability to identify slop. Now, this is one of my favorite use cases, so check this one out, for example. This guy built a real-time slop detector. So, you know about LinkedIn being overtaken by slop a little bit, right? Well, this will scroll through Twitter, and you can actually say, “Great. If you identify anything that

06:43 sounds like it was written by Claude Claude 5.1, just add slop and remove it from my feed.” You could do this for ads. And the reason why this is so revolutionary is cuz it can do it at a rate that no other model can, in terms of its speed, and it’s so cheap to do that. Now, when you make something very cheap and very fast, you genuinely unlock new use cases like this. So, you could just say, “Hey, has this been written by a person? If so, keep it. If not, get rid of it at the same time.” So, for example, what we can do here is identify if something is slop or not. You could do this to identify AI text and everything. So, I’m using the Slop

07:14 Monster, which is get rid of that I built. It’s free, the public down below. It’s like built off all the best slop detectors with some additional bells and whistles to make it really cool. So, what we’re going to do here is let’s look at illustrative costs. Now, for Astra to do this, you’re looking at $15. Jev is 4 cents, which is crazy. We’re looking at words, phrases, punctuation, rhythm, and proof. So, let’s see if it can identify slop, okay? I’ve given it a same text. Let’s run this comparison real quick and see. Look at this. Reads as slop. And it it correctly identified the punctuation cadence and it came down using my slopology framework, okay? And

07:46 it did it at lightning fast speed. Let’s give it another example. I guess it here’s another one for example. Let’s run this comparison. See, again, roots of slop. Then we come down and test whether or not it’s written by human or was it written by an AI? Let’s go ahead and see if this one works there. And again, we can try this one more time. And as you can see, it’s likely AI assisted. Astra itself can’t tell you. So this is another really cool use case. Let’s say that you have a website. I’m just going to throw this in here to my Agenty OS for a second, right? This website here we built with GPT-6 Astra. Now let’s say that you’re doing this for a client. Maybe you want to go ahead and

08:17 do different things. You can edit it. Whatever you want to do here is fine. But let’s say for example, you have this design library and we have a brief. And we wanted to identify, okay, I fed this guy’s over 300 design systems and I’m basically assessing their ability to identify what the best one would be. Well, let’s run the comparison and check. And we can pick any of the Astra reasoning. I’m going with medium just to keep it fair. Um again, I’m not even going extra high. Bam, it’s found one immediately off the different references. It’s gone through over 300 pages. That would only cost you $1.94

08:48 if you did a thousand, whereas Astra for example, $500 to do the same thing, which is crazy. Let me give you another brief example. If I do studio portfolio, okay? Now I run the comparison. Let’s see what Jev does. Jev found it. And let’s see what Astra does. Jev found it the second. Ridiculous. Astra is still going. And look, it found the exact same thing. And if you look at the difference, um $1.95 per thousand and $500. You get the idea. We could use Jev itself to classify anything you want. But if this all sounds, guys, like

09:18 I’m speaking design Spanish, I’m going to put a link down below for you to my full uh Claude code and Astra masterclass. You get full access to my entire Agentyc operating system as well as my entire courses on learning this technology, building their system, building beautiful websites, how to use it to get lightyears ahead of everybody else. I’ll put a link down below before your competitors actually grab it. Say for example, if it just needs simple and straightforward tasks, it goes to a light model. If it’s general tasks with a little more context, we send it to a balanced model like an Opus 5 or 5.1, something like that. But then if it

09:49 needs complex reasoning, we can send it to Frontier. Well, what we can do is add Dr. Jev in the middle of it. When did he get his doctorate? Somewhere between the beginning and this part of the video. Now, check this out. What I’ve done here for example is I’ve given a a query. We’re going to run it and we’re going to see basically which models it would rank it and push it through to. As you can see, it’s identified. And if you look, guys, the exact same cuz what I did with this is I basically added a bit of a description. I added all the models down here, you see? GPT Astra 6, uh Gemini 3.5 Flash, Can be K3, and all of them had a kind of a brief like route to this

10:22 model under these circumstances. And you will notice that it did that exact thing for us in the exact same order perfectly. It’s it’s really crazy. Let’s give another example. A 650K video research pack. I’ll run it again. Let’s see how fast Jev does. Again, under half a second. Astra is going all the way through. Now, the idea here isn’t to have Jev solve anything. What I’m demonstrating with this is that Jev itself is the hand. It’s a tool that we’re going to use with Astra. And when you give it this prompt, you’ll be able to set that up. Now, in terms of Jev’s intelligence, and this is really important to understand, it’s about as

10:52 smart as like a Sonnet 5. So, it’s like smart. It’s quite smart. It’s not Frontier level, but we’re not using it for that. So, the times where we do want to use it is whenever, and this is a key distinction, guys, it is one of these three things. Whenever there is a yes/no, whenever it can pick an option, and whenever there’s a score. Now, you could use any of the models you want to for this. What we’re saying here is it’s significantly faster and significantly cheaper. It’s not something that is a chat model. This is a model that’s optimized for making incredibly fast microdecisions. And people are blowing

11:23 up with their creativity on this. As you can see, people are generating UIs very quickly. Effectively, you’re only really limited by imagination. But what I would say to you is very simply this. If you can actually reduce anything down to a series of decisions, and you can quantify those decisions, you can accomplish some pretty spectacular things. But, it just brings on to an interesting question. And, that’s it. Speed and price are one thing, but capability is something completely different, which is why the next thing we need to do is learn how to 10x your capability by watching this video here together.