Jev

Um, and actually today, the-- a nice transition to that is we're gonna be talking about a type of model that's also good at something different than language models.

So I'm excited to talk about Jev.

But, um, yeah, that's, that's kind of the big news that just came out maybe yesterday, if I remember correctly.

So, um, congratulations to, uh, Fei-Fei Li and her team.

Uh, so I highly recommend that as well.

It definitely-- you'll learn a lot about AI, but it's just an interesting story of a remarkable person.

As you mentioned, Amith, we're gonna segue into a new kind of model called Jev.

That's the first topic for today's episode.

Whenever you have constrained inputs that are interacting with apps, it's...

Jev is a good thing to reach for.

This one is, is a favorite of mine because it, it represents, like, a workplace where you have multiple agents that could all have their own tasks, and avoiding collisions so that they never end up on the, the same space.

At each step, it's gonna be able to control these different agents and make sure that they get to their specific task as quickly as possible, and that they never collide or interfere with the other agents.

I'm Claire Vo, product leader and AI obsessive, here on a mission to help you build better with these new tools.

Today, I have repeat guest John Lindquist, who has done one of our most popular episodes to date on the podcast.

And here he is joining us on Jev week at How I AI to talk about our favorite new model and all the amazing product-facing use cases that he's discovered testing Jev from TypeSafe AI.

Let's get to it.

I'm glad we can all agree.

So should we talk about some other actual AI stories? James, can you explain what Jev is? Jev with a J, J-A-V.

No, I should know about this, so I'm curious to get the answer.

J-E-V? I can't even spell.

Saul Goodman is the LLM.

He can do a lot of talking.

And then the criminal guy with the bell who can't talk, but he can just ring a bell on his wheelchair is Jev.

And Jev... is essentially a neural network model that does not output text.

This new model promises 440x cheaper and 193x faster for similar use cases in Ejectic workflows and development.

Jev just came out of stealth with a differentiated System 1 architecture aimed at beating OpenAI and Anthropic for use cases requiring state and downstream probabilistic confidence in your software application layer.

If you're building with models, you'll want to hear this because at 1 400th of the price, this is a complete game changer.

Welcome to your weekly AI Clarity podcast with your signal from the noise for people building production level AI and building with AI inside real companies.

If you find some funny, we'll host them on the pod for some laughs.

And then current, what's the meta sort of updates for AI builders, your latest tips, tactics, tools, and strategies that we use ourselves on the front lines of building our AI native startup.

So today we're going to focus on TypeSafe's Jev model, which introduces a new type of architecture called System 1.

Let's go ahead and dive in.