Loading video...

Video Failed to Load

Go Home

Introducing d3-turbo, a 27B multimodal decision model with up to 128K context per question. 🤖 ⚡ 15.5× faster for 255 questions: In the team’s local test on one image, d3-turbo takes 2.12 seconds versus 32.94 seconds for d3-flash. 🎯 Make structured decisions: Returns choices, yes/no answers, and scores without...

16,146 views • 22 days ago •via X (Twitter)

6 Comments

Aaliya's profile picture
Aaliya21 days ago

Finding and tracking objects in videos sounds really useful.

Clara AI | Tools & Updates's profile picture
Clara AI | Tools & Updates21 days ago

Fast multimodal decisions with open weights could unlock powerful real-time agent workflows

Aleksandar Janca's profile picture
Aleksandar Janca21 days ago

returning choices and yes/no answers is the useful part for automation, a decision that comes back from a fixed set is one you can actually check

Veyra | AI & Tech's profile picture
Veyra | AI & Tech21 days ago

15x faster with 128K context per question is insane improvement

Hana Ai's profile picture
Hana Ai21 days ago

Structured decisions without generating text is the killer feature here

Saurs's profile picture
Saurs21 days ago

Getting really fucking tired of these claude animations. I think it's the music and sound effects, It's always the exact fucking same.

Related Videos

Jev is now multimodal. It can see. Here’s how it works and what you can build with it: Jev is a decision model. You give it information, ask questions, and get answers your code can use directly. Previously, that information was text or JSON. Now it can include images. Start with how a Jev request works. You send a “state,” which is simply the information you want Jev to examine. Then you ask questions about it. Each question specifies the kind of answer you need. → Choice picks from options you define, such as “thumbs up” or “fist.” → Noul returns the probability that something is true, such as whether a hand is visible. → Score rates something on a scale you define, such as how open the hand is. With multimodal Jev, images can be part of both the state and the questions. Put a camera frame in the state, and your questions can ask about what’s visible in it. Put a reference photo in a question’s instructions, and you can ask whether an object in the camera frame matches the one in that photo. Jev can now also identify an object and locate it for you. The new Box type brings a YOLO-like capability to Jev. Describe what you want to find, such as “the hand in this image,” and it returns a bounding box around it. Your app can use those coordinates to highlight the object or crop it. One detail matters here. Box returns coordinates even when the target is absent, so pair it with a Noul presence check before using the result. My demo asks about presence, gesture, and location together. Jev answers these independent questions in parallel, and the app combines the results. These capabilities open up prototypes for gesture controls, locating buttons in screenshots, and checking product photos against visual references. Jev’s focus on fast decisions also makes it promising for interactive applications where response time matters, with image latency worth testing in your own workflow. Images and Box are still experimental and require the images “danger zone” header. I cover how it works, the API, and the demo app in the detailed video below. Chapters 0:00 Intro 0:36 Live demo 1:41 What's covered 2:22 How Jev works 3:06 Question types 3:57 Playground demo 6:59 Demo app walkthrough 10:30 Using Multiple images 11:25 Parallel questions 12:40 Danger zone headers 13:07 Outro If you’re new to Jev and want to understand how decision models work, I’ve written a detailed article about it. It’s quoted below.

Akshay 🚀

26,832 views • 1 month ago

New short course Multimodal RAG: Chat with Videos, developed with Intel and taught by vasudevlal! In this course, you’ll work with LLaVA (Large Language and Vision Assistant), a Large Vision Language Model (LVLM) that can process both images and text. For example, given an image of a person doing a handstand on a skateboard at the beach, LLaVA doesn't just caption the scene, it’s able to predict possible outcomes, like the person losing balance or falling off. By understanding not just what's in a video frame, but what might happen next, your application can provide more insightful answers to questions about video. You'll build a full multimodal RAG pipeline that can chat about video content: - Use the BridgeTower model to create joint text-image embeddings in a 512-dimensional multimodal semantic space. - Learn video processing techniques to extract keyframes, generate transcripts using Whisper, and create captions. - Use the LanceDB vector database to store and retrieve high-dimensional multimodal embeddings. - Integrate the LLaVA model, combining CLIP's (Contrastive Language Image Pretraining) vision transformer with Llama, for advanced visual-textual reasoning. Your final system will ingest video data, generate embeddings for frames and text, perform similarity searches for relevant content, and use the retrieved multimodal context to inform LVLM-based response generation. The result is a system capable of answering nuanced questions about video content, effectively chatting about the video it has processed. Please sign up here!

Andrew Ng

107,967 views • 2 years ago

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.

Ben Dicken

42,183 views • 1 month ago

What Jev actually is, why it's so fast, and what you can build with it. Classification is as old as AI that can read: give it text, ask a question with fixed answers (complaint yes/no · which team · urgency 1–5), and the label drives a rule. The problem: we've been using models built for writing, a few seconds per answer. Jev (TypeSafe, launched Sept 15, founded by one of the OpenAI researchers behind ChatGPT's instruction-following) only decides. It never writes. Send the text once with every question; it scores every answer in one pass: yes/no, pick one, or a score, each with a confidence. 70–500 ms. Input ~$0.042 per million tokens, output free. TypeSafe measured up to ~200× faster and ~400× cheaper than top models on its own workflows, and says real-world gains are usually lower. Builders: a resume screened against 6,000+ companies in 25 seconds for $0.37; 98,000 items labeled in ten minutes. ~13% of paid Vercel AI Gateway teams used it within a day. Calibrated: "70% sure" should be right ~70% of the time, so software can act alone above a threshold and route the rest to a person. Build with it: every competitor ad, same five questions · every ticket, review, call note and CRM entry across systems, tagged the same way · an agent's actions checked before they run (LangChain already does this). Edges: text only; weak at math, counting, dates; reads your question literally; you design the questions and categories up front. That design is the skill. #jev #aiagent

Professor Glitch

38,900 views • 1 month ago