Go to paper.design, download the desktop app, open Figma, copy, paste in paper. Problem solved.

Every dev that has to design should use @paper + @mobbin. Nothing will make your life as easy as this combo.

Man, these model release are coming after my wallet. Just when I had switched to Codex, Anthropic releases this 🫠

Limit reached in one prompt. Astra is a token hungry 🫠

I think it's important to have healthy role models. With everything going on online, it's really a good thing to have people showing that healthy and happy marriages still exist. The youth deserves to know what marriage is all about. "The pursuit is forever." Everyday we have to seek the wellbeing if our partner, submit to each other and seek the utmost interest of the people we're with. It's a selfless endeavor, contrary to what people are tought by the internet. I'm soon to be married, and I can't wait to be going home to my beautiful wife with gift and flowers, and see her smile every single time till God calls us home.

Wonderful user experience

This is genius - when I’m on a phone call and I open Revolut It has this big warning banner to prevent getting scammed

Wow, tons of people are working on that. Some time back I saw Buzz by Block, but after using it for some time, I think it’s not really it. At least not yet. Saw Nebula, but there it feels like it’s lacking as well. I think there is something that is waiting to unlock a better way of communicating for work with humans and agents. I believe it’s a UX problem, but we’ll see how it goes.

Jev is cool. So is it's OSS companion, Laya. The Latest Cool Thing In AI™ tends to get a lot of hype, sometimes without everyone even understanding it. So... what is this thing? Jev is an AI model that consumes input and produces output VERY differently than chat, claude, grok. The input is two things: 1) Text state to assess. Email, html, code, whatever. 2) A set of questions which will be asked about the attached state. The canonical example from TypeSafe's docs is to identify the urgency of a support ticket. We pass the model the customer text + a single noul question "is this urgent?". Jev returns a full set of JSON. This JSON is not generated with token-by-token autoregression. Jev is not trained to produce sequences of text tokens, rather to answer questions, and guarantees well-formed responses. In the example below, we see it produces a 0.99 probability (on a 0-1.0 scale) that the answer is "yes." Jev supports exactly three types of questions (seconds example in video): a) Noul: 0–1 probability that the answer to a yes/no question is "yes." b) Choice: Ask question with pre-defined set of answers. Jev chooses the best and assigns probabilities to each. c) Score: Ask question with pre-defined scale of answers. Jev produces a position on the scale. Jev computes answers for all questions in parallel, making responses super fast even for many questions in a single request. This might seem like a narrow set of capabilities, but in the right contexts leads to incredible potential. It also makes for a useful API / primitive for programming, since the outputs are... *ahem*... type-safe and predictable in structure. Jev is not going to replace LLMs for writing your code, auto-generating your docs, or being at the core of an agent harness. But Jev IS incredibly cool, and will be used to build a lot of amazing tech. Hope this helps.

as a former neuroscientist, can't emphasize how much system one is important to real intelligence why do we need a dumber but fast model (system one, unconscious) in our brain? it frees the slower but smarter model (system two, conscious) to focus on what really matters, making it a lot better as a human, i can consciously control my body/hand, etc, but if i do that, i can't really be doing other tasks that require intelligence. similarly, gpt 6 astra is extremely intelligent, & you can control a robotic hand with it, but if won't be able to do frontier math if it's context window is polluted with robot hand vision/control tokens combining a powerful smart model with a faster, dumber, but still very intelligent model is the way to go very excited about this line of research

Two reasons Jev is an overnight success (two years in stealth, btw). And they’re complete opposites of each other: 1. Jev unlocks a whole new class of low latency classification and decision features. 2. Folks are doing the math. They’re realizing they’re using expensive LLMs for a huge number of decisions Jev can make faster and for a fraction of the cost. In some cases, the potential savings are an order of magnitude.

20x 👀

everyone is talking about Jev’s cost/speed, but ARE YOU KIDDING ME classification problems are everywhere, and now you telling me that you don’t need to build your own classifier, and this classifier has world knowledge already 😵😵😵 this is why it’s a big deal most areas/products where classification ML was still hard due to lack of skill, cost, or infra should get this out of the box and plug in across the workflows & instantly feel it - this may unlock a lot more real value faster than LLMs 🫡

I think Jev unlocked something much bigger than decision making. It made me wonder how many things we use LLMs for today that simply don’t need a generative model. Jev can become the decision layer. But what happens when retrieval, context, memory, grounding, perception and other parts of intelligence get their own specialized models too? Maybe the future of AI isn’t one massive LLM doing everything, but a stack of specialized intelligence, with LLMs doing what they’re actually good at. I’m really excited to see what will be possible in the future.

Wow, this is crazy. Congratulations @typesafeai 🎉

Man. The possibilities with this 😁 Time to go back to design systems. Fun times ahead.

I’m loving this new way of going about things. Prices will go down. For builders this is good news.

It's all coming together 🔥

New experiment: json-render + jev The future Generative UI is instant Your components, your actions, your design system Rendered in milliseconds

everyone is trying to understand wtf Jev actually is and does. CJ has you covered. This one really opened it up for me. piped.video/watch?v=QbYBRjOa…