TypeSafe's new model can't write a sentence. It just makes fast, cheap decisions, and a growing list of builders are already wiring it into email triage, trading bots, and self-driving demos.
Posted
yesterday
Duration
Format
Demo
educational
Views
72K
912 likes
57 · 43
Big Idea
The argument in one line.
Jev is not a chatbot: it reads context like an LLM but only ever returns a fixed-shape verdict, and that constraint is what makes it dramatically faster and cheaper to run at volume than a generative model.
Who This Is For
Read if. Skip if.
READ IF YOU ARE…
You're building an AI agent and want a cheap, fast layer to route or pre-filter requests before an expensive model gets involved.
You're drowning in email, DMs, or comments and want an automatic triage layer instead of reading everything yourself.
You build real-time systems, trading bots, browser agents, simulations, where per-decision speed and cost matter more than conversational ability.
You want a plain-English explanation of what a non-generative AI model actually is and how it differs from a chatbot.
SKIP IF…
You're looking for a chatbot, writing assistant, or anything that generates text. Jev never writes.
You want independently verified benchmarks. The speed and cost numbers here are TypeSafe's own claims, not third-party tests.
TL;DR
The full version, fast.
TypeSafe, founded by a ChatGPT co-inventor, released Jev: a model that reads language but never writes any, returning only a structured verdict, a choice, a 1-5 score, or a yes/no probability, instead of generated text. That constraint is what TypeSafe claims makes it 20 to 200 times faster and 40 to 400 times cheaper than a comparable LLM call, about 0.4 seconds and $0.0004 per decision versus roughly 10 seconds and 3 cents. The presenter demos it live: routing a coding agent to the right model tier, sorting 500 emails by category, importance, and scam likelihood in seconds, and pointing to outside builders using it for a Tesla self-driving sim, a crypto trading bot, and a 7-second flight-booking browser agent. Access is via TypeSafe's waitlist or the Vercel AI Gateway.
Free for members
Chat with this breakdown — free.
Sign in and you get 23 free chat messages on us — ask for the hook, quote a framework, find the exact transcript moment, generate a markdown action plan. Bring your own key when you want unlimited.
Riley teases Jev, a new non-chatbot AI model from TypeSafe, and shows it triaging 500 of his emails before explaining what it actually is.
02:08 – 03:56
02 · Model router demo
A single-prompt coding agent built with Jev picks which underlying model, nano, balanced, or frontier, should handle each incoming request based on how hard the task looks.
03:56 – 05:19
03 · What is Jev?
TypeSafe is the company, founded by a ChatGPT co-inventor. Jev is the model. It reads language like an LLM but never writes any, it only returns a verdict and a confidence score.
05:19 – 11:14
04 · Choice, Score & Null
Using a custom email app, Riley demos Jev's three response types live: a null (probability an email mentions a brand deal), a choice (email category), and a score (importance level), each run across all 500 emails in seconds.
11:14 – 13:04
05 · Structured output, speed & cost
Because Jev can't generate text, it skips the LLM's usual generate-then-format-then-parse pipeline. TypeSafe's own benchmark claims about 0.4 seconds and $0.0004 per decision versus roughly 10 seconds and 3 cents for a comparable LLM call.
13:04 – 15:36
06 · Monitor everything
Riley adds a new null asking whether each email looks like a scam. Jev flags 55 of 500, about 10%, and he argues that tagging and routing everything automatically is where he's most excited to use it.
15:36 – 16:20
07 · Context window
Jev's context window is 64,000 tokens, about 6% the size of a frontier chat model's, a real constraint on how much reference data it can weigh per decision.
16:20 – 20:18
08 · Real-world uses & how to get access
Outside builders' demos: a Jev-powered Tesla self-driving recreation, a crypto trading bot, and a 7-second flight-booking browser agent. Access is via TypeSafe's waitlist or the Vercel AI Gateway.
Atomic Insights
Lines worth screenshotting.
Jev is not a chatbot: it reads language like an LLM but never generates any, so there's no output-token cost because there are no output tokens.
Every Jev response is one of exactly three shapes: a choice from predefined categories, a score on a scale the developer names, or a null, a yes/no answer expressed as a probability.
TypeSafe claims Jev runs a decision in about 0.4 seconds for $0.0004, versus roughly 10 seconds and 3 cents for a comparable LLM call, a claimed 100x gap on both speed and cost.
Because Jev can only return a fixed structure, it skips the usual LLM pipeline of generating text, formatting it as JSON, then parsing it back out.
The presenter fed 500 real emails through a custom app and had Jev tag each one with a brand-deal probability, a category, and an importance score in under 15 seconds per pass.
Jev flagged 55 of 500 emails, about 10% of the inbox, as likely scams, showing how a near-free classifier could replace manual spam triage.
Jev's context window is 64,000 tokens, about 6% the size of a frontier chat model's million-plus token window, a real limit on how much reference material one decision can weigh.
One builder recreated a Tesla-style self-driving demo by having Jev repeatedly choose from a small tree of driving options, continue, turn, stop, based on the current scene.
Another builder wired Jev into a crypto trading bot that decides buy, sell, or hold every few hundred milliseconds because the output space is small and fixed.
A browser agent powered by Jev booked a one-way flight from Zurich to London in about 7 seconds by treating each screen as a fast multiple-choice decision instead of a slow generative one.
Jev is accessible two ways right now: TypeSafe's own waitlist, or immediately through the Vercel AI Gateway with an API key.
The bigger claim is societal: a classifier this cheap could run over every inbox, DM, and comment section, filtering slop and cold outreach before a human ever sees it.
Takeaway
The AI model that never writes a word, just decides
WHAT TO LEARN
A model that returns a verdict instead of generated text can run orders of magnitude faster and cheaper, and that changes what's actually worth automating.
01Intro / cold open
A model can be genuinely new without being a chatbot. Jev can't write a sentence, it only classifies, and that limitation is the entire value proposition.
Watching an unfamiliar demo before the explanation starts is a legitimate way to earn attention, show the result first and back into how it works.
02Model router demo
A cheap, fast classifier is well suited to sit in front of an expensive model and decide which tier a request actually needs.
Task difficulty, not user intent, is what should route a request to a bigger or smaller model.
03What is Jev?
Classification means sorting an input into a small number of categories decided in advance, never producing open-ended text.
A model with zero output tokens has no output-token cost. That's a structural pricing advantage, not just a discount.
04Choice, Score & Null
Every automated judgment call reduces to one of three shapes: pick one option, place it on a scale, or estimate a probability. Design which shape fits the question first.
The quality of a score or probability depends entirely on how precisely you word the question and its yes/no anchors, not on the model alone.
Running the same classifier across hundreds of items in seconds turns 'read your whole inbox' into 'read the six flagged emails'.
05Structured output, speed & cost
A model that generates text, formats it as JSON, then gets parsed pays for three steps where a pure classifier pays for one.
A large claimed gap in speed and cost only matters at volume. Tens of millions of daily decisions is where cents per call becomes real money.
06Monitor everything
The same technique that scores importance can score scam likelihood: one classifier, many separately defined questions, run over the same data.
A near-free classifier changes 'monitor everything' from an expensive engineering project into a checkbox.
07Context window
A smaller context window is a real tradeoff, not a footnote. It limits how much reference material a single decision can weigh.
08Real-world uses & how to get access
Any decision with a small, fixed set of outputs, turn left or right, buy or sell, click this or that, is a candidate for a classifier instead of a generative model.
Fast per-decision latency compounds. An agent making dozens of small structured choices per screen can finish a multi-step task in seconds instead of minutes.
Existing infrastructure you already have access to can be faster to build on than waiting on a new company's waitlist.
Glossary
Terms worth knowing.
Jev
TypeSafe's frontier classification model. It reads text and other input but never generates any, returning only a structured verdict instead of a written response.
Classification
Sorting an input into one of a small number of categories decided ahead of time, rather than generating open-ended text.
Null (Jev output type)
A yes/no style Jev response expressed as a probability, for example 91% confident the answer is yes, rather than a plain true or false.
Score (Jev output type)
A Jev response placed on a scale the developer defines in advance, such as 1 (ignore) through 5 (critical).
Choice (Jev output type)
A Jev response that picks one option from a predefined list, such as sorting an email into a named category.
Context window
The maximum amount of text a model can weigh at once when making its decision. Jev's is 64,000 tokens, much smaller than a typical chat model's.
Model router
A system that inspects an incoming request and picks which underlying AI model should handle it, based on how difficult or costly the task appears to be.
Vercel AI Gateway
A hosted proxy that gives developers API access to multiple AI models, including Jev, without integrating each provider separately.
“It is 20 to 200 times faster, 40 to 400 times cheaper, optimized for decisions.”
Cold, quotable launch stat with no setup needed→ TikTok hook↗ Tweet quote
05:01
“The LLM predicts the next word one word at a time. Jev will just respond with yes, it is 91% confident in yes, or it is 90% confident it falls into this category.”
Sharp contrast between how a chatbot and Jev actually answer→ IG reel cold open↗ Tweet quote
11:38
“Because Jev can't write at all, structure isn't part of the request. It's the only thing it can return.”
One-line thesis for the whole video→ newsletter pull-quote↗ Tweet quote
12:04
“It's around 0.4 seconds and 0.0004 dollars per decision.”
The headline economics number, easy to caption over a stat card→ TikTok hook↗ Tweet quote
18:38
“This model Jev is able to move so much faster than if it's powered by an LLM.”
Sets up the flight-booking browser agent payoff→ IG reel cold open↗ Tweet quote
The Script
Word for word.
Read-along
Don't just watch it. Burn it in.
See every word as it's spoken — crank it to 2× and still catch all of it. The same dual-channel trick behind Amazon's Kindle + Audible.
17px
metaphoranalogy
We have huge news in the world of AI. A company called TypeSafe just released a new type of model that's very different from the other models I talk about regularly, like GPT -6 Astra and Fable 5 .1. This new model is called Jev, and it's not a chatbot.
It can't even write a sentence. It simply makes smart decisions way faster and way cheaper than any of the other models. In this video, I'm going to show you three examples of tools I built with this new model, Jev.
And I'm also going to explain the 10 things you need to know about this model before you start using it. So I just had Claude create this app for me that uses Jev. Watch how fast Jev is going through 500 of my emails.
And so it is running through all my emails. It's gone through 80, 90, 100, 110, 120, 130. And you can see here that it's actually...
categorizing every single email. It's deciding when we need to respond. There's a lot of emails I need to respond to today.
I'm not that great at checking my email. And you can see here, it's going through all of these and it is done. It has gone through 500 out of 500 emails and then it creates this pie chart of all of the different types of emails that I've received.
And you might be thinking, okay, Riley, that seems pretty cool, but like... what the hell is it? And don't worry, we are going to be talking about the 10 things that you need to know about Jev in order to start using it.
The first thing I want to talk about, however, is the launch video. So a few days ago, Diogo Almeida, he said, after co -inventing ChatGPT, I kept asking myself, why have superhuman chat models not led to AGI? I've spent the last two years in stealth building a new way to train models.
RLCD, and a new type of frontier AI model that we are releasing today, Jev. It is 20 to 200 times faster, 40 to 400 times cheaper, optimized for decisions. And we'll get into what that means in just a second.
Right before I filmed this video, I created an AI agent that has a model router that uses Jev. So based on my input, It will use Jev to immediately decide which model it should use.
And I created this in a single prompt using Cloud. I'll show you the prompt in just a second. But let me show you how this works.
Hey, I'm Riley. Now, this is a very simple request. It should use a very cheap model for this.
There's no need to use a really powerful model. Watch what happens. I'm going to hit send.
And Jev immediately selected Nano, which is the smallest model. Let's go up the stack a little bit. So I'm going to refresh.
I'm going to say, hey. I'm Riley. I want to build an app that uses AI.
ET wrapper. Tell me the best way to do it. Now, I don't think this will be like Frontier.
I think this might be one level up. It might use a model slightly smarter than Nano. And look at that.
It actually selected using Claude Sonnet 5, which is this balance, right? There's Tiny or Nano. fast, balanced, and frontier.
And I created this agent that can search the web. It can generate files. It can actually vibe code.
I created this in a single prompt, and it's pretty cool. And so here it says, please, I'm going to say, please, can you generate all of the code for this? Make sure it's perfect.
Now, I don't think it's going to do the frontier. I actually haven't gotten it to select frontier. But as you can see here, it is 95 % sure that it should be this balanced model.
And what Jev is made for is to make really fast, high -quality decisions for incredibly cheap. Okay, the first thing that I realized about Jev when I was talking to my friends about it... They said it's really good for classification.
So what does classification even mean? Classification is a way of sorting an input into a few boxes that you've named ahead of time, right? If we were to have this set up on our email, it basically sorts them into categories.
It's like a customer question, a sponsorship, or it's spam. This model is really good at accurately and quickly sorting it into a predefined category. So what is TypeSafe AI?
And so TypeSafe AI is the name of the company. Jev is the model. The guy who worked on ChatGPT left to start a company called TypeSafe.
And then they just released their model called Jev. So is Jev an LLM? And so they say, no, it is not an LLM.
It reads language like an LLM, but it never writes any, right? That's why there's no output token cost because there is no output tokens. It just spits out a verdict and how sure.
it is the llm predicts the next word one word at a time or one token at a time jev will just respond with yes it is 91 confident in yes or it is 90 confident it falls into this category okay so this is actually the most important thing that you need to understand about jev when you're using it for the first time and that is how does it actually respond and what are the different types of responses Let's go over all three types of responses.
So this model will respond in three ways. It's either a choice, a score, or a null. A choice is like multiple choice, right?
It fits into one of your predefined choices. That's how it does categories. Now there's also a score.
So you can create a scale, and you get to decide what the scale is, and I'll show you how that's created. And then there's also a null. How likely is this true?
To illustrate the different types of outputs that Jev can have, I made some changes to my email app, which gives us full customizability over the inputs and the outputs. So here we can see that we can add a choice. We can add a score or a null.
Let's start with the simplest one, which is a null, right? Where the answer is just a probability of yes. So remember, we're analyzing 500 of my emails.
If we click null, we could say something like mentions a brand deal opportunity. And so then, since all of this information will be sent into Jev when it runs, and that's how it predicts how confident it is in yes or the probability of a yes, we want to make sure that we give good answers here. Does the email mention an opportunity?
for sponsorship in Riley's content. So it's only going to be looking for emails that mention a brand deal opportunity. So let's go ahead and run this.
And notice here, this is the null style output, right? And so most of them are very low, right? They just don't mention anything, but some of them are green, meaning there's above a 50 % chance that it mentions a brand deal opportunity.
And so we can scroll down. Here it's Riley Wick Symphony. Hey Riley, how are you?
I've been following your AI content. And so this one commands a brand deal opportunity. This one is 90 % sure.
And it went through all 500 of them. So that is a null. Now let's go ahead and add another one, right?
So we can add another one, which is a choice. So here we are going to add category of email. And so, what is the category of the email received by Riley?
And we could say brand deal. We have brand deal, subscription update, cold pitch, newsletter, and agent native. Here for this, I put very specific emails and we're going to call this agent native.
And so now we have five options. I'm going to hit save. Now check this out.
When I hit save, It added category. So now we have category of email here.
So let's go ahead and run Jev again. And as you can see here, that is the second option. This is a null, which is like probability of a yes.
And here is a category of email. And here is the confidence of its response. And we can see the category.
And it did it immediately, right? Look at that. 500 emails in a matter of seconds.
all analyzed, and now we have the category of email, which is really cool. Okay, so now we have one more type of output that we can create. We've done a null, we've done choice for categories, now we can do score.
So we just added a score, and here you can create a scale. And so I'm just gonna go, I think importance is actually pretty good. How important is it Riley personally sees email about?
Given about Riley. And these are all variables. So it's just like how important is it that Riley personally sees email and the data from the email will be placed in there.
And then given about Riley. And so about Riley is just this right here. And so we're creating a scale.
Ignore, low, medium, high, critical. And we can add one more. We can call this like hyper.
Let's call this insane.
needs response within 30 minutes or bad things happen. So again, this is a score and it's scoring its importance. And you get to decide as a person who's using Jev, the different scale.
Ignore low, medium, high, critical, insane. Okay, so now we're gonna save this. And whenever we save it, the data gets reset.
And again, we have the null, which mentions a brand deal opportunity. That is either yes, it's measuring the probability of yes, the category, choosing between different options, or a score, which will place it in the scale. So now we can run it, and let's see the importance of each email.
Look at how fast this goes. And it even has it on the scale right here, which is pretty cool. And just like that, I think that was 12, 13 seconds.
We have all the emails analyzed. 500. Or classified.
And here we have none of them were insane. None of them. Six were critical.
And we can actually click on critical. And we can see the exact performance. And so we can actually click directly on the category.
And there you go. It categorized all of those emails. So those are the different types of outputs that Jev can do.
So there we go. The outputs are choice, score, and null. Now I want to talk about something a little bit different, which is couldn't LLMs already do a structured output?
And the answer to that question is yes. But it was really inefficient, right? Think about asking a chatbot to give you an output, and then it would actually need to format its output as JSON.
And because Jev can't write at all, structure isn't part of the request. It's the only thing it can return. This model is returned to respond in a structured fashion, right?
So the LLM would need to generate text, format that text, and then parse the text into all of that information that shows up here, right? If we look at all of this, like an LLM has to do a lot of work to format it like this. Whereas this model that we have right here, Jev automatically formats it.
in the exact format. And that's why there's only three different options. It will do it perfectly every single time.
It will do it more efficiently because it doesn't waste any tokens on the text portion. And the next question that a lot of people have about this model is like, how fast and how cheap is this model? And we can take a look at it here.
So based on their own benchmarks, it's around 0 .4 seconds and 0 .0004 dollars per decision. Very small cost.
Whereas a traditional LLM would cost somewhere around 3 cents and take 10 seconds. I know 3 cents doesn't sound like crazy, but if you're doing tens of millions of requests per day, it starts to add up incredibly fast. And look at how much cheaper it is.
So it's cheaper in cost per decision, and the time per decision is way different. 0 .4 seconds versus 10 seconds. Okay, so how am I excited to use it?
And very simply, I'm going to monitor everything. The same way that I just set up my emails, right? I was able to monitor every email and categorize it and create a level of urgency.
And you can basically monitor everything really quickly. You could do this about everything, not just your emails, but you could do your DMs across social media platforms, comments, sponsorship pitches. Every single thing gets tagged and potentially routed to the correct person within the company.
This will allow me to organize all of the information that comes into my company. And so that is one thing that I'm really excited about. And then I was thinking at a societal level, right?
Think about how much slop there is at the societal level. If we were to get models like Jev that are especially multimodal and can analyze videos, we could basically filter out all of the slop. Additionally, if this is used in email, it'll filter out all of the cold emails, the scams.
you could very easily say, is this email a phishing scam? And we can actually do this right now. We could actually create a new null.
We create a new null, right? Is this a scam of any kind? Does this email look like a scam or something untrustworthy?
We could actually save this. And I'm going to say, is this scam email?
Save. Now we have this new one. Is this a scam email?
And we can run it and it will check on how many of them are a scam. And look at this. We're at 35, 39, 43, 44, 47, 51, 55.
Out of 500 emails analyzed, 55 of them were scams. And it was recognized just like that. Some of them are more confident in others, right?
This is a 54 % chance that this is a scam. 71 % chance that this is a scam. But that's 10 % of my email inbox, which is crazy.
And so I think this may be how notifications work in the future, right? There should just be this filter that you have personalized for you. which filters out scam or cold emails, which I think is really cool.
And what is the context window? So the context window is smaller. Remember, all of this stuff is actually sent to the AI as it's in its context.
And remember, there's only input tokens for this model. So the context window is 64 ,000 input tokens. So if you compare this to Astra, which is 1 .5 million, This is actually only 6 % of Astra or the best models in the world like Fable 5 .1, which are around a million context window.
This context window is only 6 % of that. So it's much smaller. I wonder if they're going to create a bigger one so you can add in more context about your business as it's doing the classification.
But that is the context window. Okay, and finally, how are other people using this model? Let's take a look.
So here's Justin Schroeder on Twitter. this is very interesting i'm going to turn this up to 1 .25 speed and let's watch this video okay this new uh jet model is really something else it's different than the other ones because it's not an lom it's basically a classifier it's fancy classifier but it's a general purpose classifier and so it's able to make decisions that uh are Pretty good, but you have to give it the options that it's going to take.
So here I was able to recreate Tesla autopilot in basically no time at all. I'm not driving this. It's making its own choices about where to go.
You basically give it the tree of options. Remember, we talked about how you have to actually give it the tree of options. So it created a, just like the categories or a choice, it has predefined choices, which is probably continue going straight, turn left, turn right, straighten out.
I don't know how many choices he had. but he was able to at any given point or in certain intervals, the Jev model that's running in his application is deciding which option to take based on all of the data around it. Then it's able to decide.
So like it's reading that there's a red light there right now and that it needs to stop for it. It knows about the pedestrians. Okay, so this guy, Jared, is actually using it in real time.
It's analyzing the stocks and it's determining whether it is a buy or sell and it has the confidence and it's actually making, trades. And you can actually see the demo here at jevtrader .vercell .app.
And this is really cool. And this will be used, or models like this will be used to do trading or other gambling nonsense. It's just a perfect model for it.
Very fast decisions based on a set of inputs. And because trading is either buy, sell, or hold, It's a very simple set of outputs.
You want something smart and fast and cheap because you want it to run over and over and over again. You basically want this to run every second. And so that's what makes it really good for finance use cases like trading.
And so the last use case I want to talk about is browser use and browser agents. So look at this. Because this model is so fast and every frame on your browser is basically a set input, This model Jev is able to move so much faster than if it's powered by an LLM.
Check this out. So it's literally filling in the browser. It's booking a flight incredibly fast.
And this is Jev. And so it only took around seven seconds to get through this screen here when booking a flight. And in order to use it, there's actually a couple of ways that you can use it.
You can go to TypeSafe and try and get off the wait list.
pretty early so you can get on the waitlist at typesafe .ai but also the model itself is on the Vercel AI Gateway. You basically want to go to Vercel and then down here you have your AI Gateway and you want to get your API key for this AI Gateway because this model Jev is actually on the AI Gateway. So if you get the AI Gateway key you can literally go to Claude or Codex.
I normally use Codex. I'm just out of credits on Codex. And you can just say, hey, I want you to create an app that uses Jev.
And this app, here is my Vercel AI gateway key. Use Jev. Look up the docs.
I want you to use Jev and create an app with Jev. It's created by TypeSafe. And this will allow you to create an app.
Your AI can go off and learn about Jev, and it will create whatever app you can think of. Anyway, go out there, test this model. Let me know in the comments how you use it.
What apps are you creating with Jev? What are you most excited about? Or is this super overhyped, right?
Am I overhyping this? Please let me know in the comments and I'll see you here for the next video.
The Hook
The bait, then the rug-pull.
Riley Brown opens with a live demo before he even names the model: watch Jev sort 500 real emails into categories in under 20 seconds, then he rewinds to explain what TypeSafe's new model actually is and why it can't write a single word.
Frameworks
Named ideas worth stealing.
05:42list
Jev's three output types
Choice
Score
Null
Every Jev response fits one of three shapes: a multiple-choice pick from named categories, a score on a defined scale, or a null-style yes/no probability.
Steal forany classification or triage layer for inbound requests, emails, support tickets, DMs, comments
01:30list
10 things to know about Jev
Launch context (TypeSafe, RLCD)
Is Jev an LLM?
How it responds (choice, score, null)
Couldn't LLMs already do structured output?
How fast and cheap it claims to be
How I'm excited to use it (monitor everything)
How it changes society (a filtering layer)
What is the context window
How people are using it now
How to get access
The presenter's own framing device, a numbered whiteboard list walking through what a builder needs to understand before using Jev.
Steal forstructuring any new-tool explainer video around a numbered checklist
CTA Breakdown
How they asked for the click.
VERBAL ASK
19:08link
“you can go to TypeSafe and try and get off the wait list... but also the model itself is on the Vercel AI Gateway”
Gives two concrete access paths (waitlist or existing Vercel infrastructure) and a copy-paste prompt to hand a coding agent, lowering friction from watching to building.
Add Modern Creator as a preferred source and Google shows you more of our breakdowns in Search, Top Stories, and AI Overviews. It only changes what you see, and you can undo it in your Google settings anytime.
Add to Preferred SourcesOpens your Google source preferences with us pre-loaded. Tick the box and you're done.
A 22-minute weekly roundup covering the open-source model that finally passed the vibe check, Codex screen-to-skill recording, the SpaceX/Cursor acquisition, and two Claude updates.
A 33-minute field guide to the nine structural shifts in AI agents — what's permanent, what's changing, and the five human foundations that will matter most.
Riley Brown wires ChatGPT's new Work mode into eight always-on automations, from a daily commitments tracker to a fully scheduled monthly business review.
One creator spent a week and $1,500 in credits with early access to OpenAI's new model and came away with seven reasons he thinks the agent era just changed.
00:17
00:32
00:53
01:08
01:23
01:38
01:54
02:24
02:39
02:55
03:10
03:25
03:40
04:26
04:41
04:56
05:12
05:42
05:57
06:13
06:28
06:43
06:58
07:13
07:29
07:44
07:59
08:14
08:30
08:45
09:00
09:15
09:30
09:46
10:01
10:16
10:31
10:47
11:02
11:32
11:47
12:03
12:18
12:33
12:48
13:19
13:34
13:49
14:04
14:20
14:35
14:50
15:05
15:21
15:51
16:06
16:37
16:52
17:07
17:22
17:37
17:53
18:08
18:23
18:44
18:59
19:24
19:39
19:55
20:10
22:18
33:38
27:33
20:07
23:59
Video of the Day54:22