正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

does Jev understand colour? incredible model, very cheap and fast. definitely feels like a leap forward for creating new UX/UI paradigms on top of modern language models.

Matt DesLauriers

61,926 subscribers

538,524 次观看 • 12 天前 •via X (Twitter)

艺术科学技术

Anya Rossi• Live Now

Private livecam show

36 条评论

gsimone 的头像

gsimone12 天前

are you doing a scoring of a big palette of colors for this?

Matt DesLauriers 的头像

Matt DesLauriers12 天前

16 predefined colors ( and just rendering their weighted probabilities

gsimone 的头像

gsimone12 天前

clever, love it

Alexander Chen 的头像

Alexander Chen12 天前

Very cool!

Nate 的头像

Nate12 天前

This is great can’t wait to experiment with it

Mahmoud Ramdane 的头像

Mahmoud Ramdane12 天前

This is amazing i’d olay with this on an iphone- care making it a website? 😂

Matt DesLauriers 的头像

Matt DesLauriers12 天前

I would probably run out of tokens pretty quickly... 😅 we need a OSS and WebGPU/client-side version for that.

Mandar Wagh 的头像

Mandar Wagh12 天前

colour naming is a good test for this: people agree on focal red and split on teal or maroon. with 16 fixed swatches the number I would want is how often two people pick the same swatch for a word, and whether Jev lands inside that spread. have you tried the contested ones?

Basel Ashraf 的头像

Basel Ashraf12 天前

For some reason it doesn't understand sound but can do everything else.

Dale Cloudman 的头像

Dale Cloudman12 天前

Oo do a quantized 16x16 grid with 256 hex choices ! It should fit ..

Tim 的头像

Tim12 天前

haha love this. live design personalization in the future? have added it to

Marc Krenn 的头像

Marc Krenn12 天前

Love it! :)

Aapakari 的头像

Aapakari12 天前

Add custom palette injection for real UX work instead of fixed 16. 🎨

Fluxora 的头像

Fluxora12 天前

That's wild altogether 💪🏻 Exciting times for creators like us isn't it

機械太郎( KikaiTaro ) 的头像

機械太郎( KikaiTaro )12 天前

共感覚の研究に使えるかもしれない。

arikami 的头像

arikami12 天前

satisfying to watch

M 的头像

M12 天前

this is sci-fi stuff man

Mihovil Ilakovac 的头像

Mihovil Ilakovac12 天前

This is one of the most fun uses I've seen around. I watched till the end 😂

Pronsh 的头像

Pronsh12 天前

i love this usecase

Salise 的头像

Salise12 天前

that model sounds really promising for fresh UX/UI ideas, can't wait to see what people create with it

MrT🧢 的头像

MrT🧢12 天前

@shadcn 👀

party anima 的头像

party anima12 天前

wait this is so sick what the hell

John Rood 的头像

John Rood12 天前

the UX unlock is model judgment getting fast enough to feel like input handling.

badtripllama 的头像

badtripllama12 天前

damn impressive

Edo 的头像

Edo12 天前

follow

Dušan Gavrilović 的头像

Dušan Gavrilović12 天前

wow. very cool idea

Lukas Caha 的头像

Lukas Caha12 天前

Omg extremely useful, I am going to steal this

Alexandre Malfreyt 的头像

Alexandre Malfreyt12 天前

@dhh that would be incredible for fast custom themes on Omarchy 👀

mewc 的头像

mewc12 天前

This is unreal

Ondřej Bárta 的头像

Ondřej Bárta12 天前

All I need right now is for this to be on-device, and we can make so many things in software so much better!

srikar 的头像

srikar12 天前

cooking

Valentin Brajon 的头像

Valentin Brajon12 天前

Wow, nice idea Matt !

Jake Mauldin 的头像

Jake Mauldin12 天前

wild part is nobody taught it colour. it learned "matrix = black and green" from how we write. that bar is basically a readout of what branding has already put in our heads

战忽局预备役的头像

战忽局预备役12 天前

看起来把置信度也用起来了

Andrey 的头像

Andrey12 天前

this is beautiful

karen 的头像

karen12 天前

such a cool demo! i didn't realize it's that fast

相关视频

VLAs? WAMs? Are language and video models the right foundations for robotics? Introducing Grounded Action Model (GAM): a new paradigm that builds robot foundation models on top of a pretrained 3D grounding model. Ground first. Then learn to act. 🧵👇

VLAs? WAMs? Are language and video models the right foundations for robotics? Introducing Grounded Action Model (GAM): a new paradigm that builds robot foundation models on top of a pretrained 3D grounding model. Ground first. Then learn to act. 🧵👇

Jiafei Duan

679,492 次观看 • 8 天前

I got early access to TypeSafe AI's new Jev model and built a demo of it playing tetris The generation speed is so fast that it's pushing blocks down This feels like another "this changes everything" moment

I got early access to TypeSafe AI's new Jev model and built a demo of it playing tetris The generation speed is so fast that it's pushing blocks down This feels like another "this changes everything" moment

Marcus Lowe

79,908 次观看 • 13 天前

It's incredible how this scene from 'Legend of Sleepy Hollow (1949)' surpasses many modern action films. The chase is fast-paced, urgent, and genuinely terrifying. On top of that, the visual design is stunning, every frame feels like a meticulously crafted painting.

It's incredible how this scene from 'Legend of Sleepy Hollow (1949)' surpasses many modern action films. The chase is fast-paced, urgent, and genuinely terrifying. On top of that, the visual design is stunning, every frame feels like a meticulously crafted painting.

old toons

150,383 次观看 • 1 年前

The new DeepSeek V4.1 Flash model is mindblowing - back on top of the open-source model leaderboard and extremely cheap. It has a lot of very smart ways to be efficient and highly capable so I made a video of the forward pass to give you a view of what going on inside the model during inference. Read more at And find the weights at

The new DeepSeek V4.1 Flash model is mindblowing - back on top of the open-source model leaderboard and extremely cheap. It has a lot of very smart ways to be efficient and highly capable so I made a video of the forward pass to give you a view of what going on inside the model during inference. Read more at And find the weights at

Thomas Wolf

65,923 次观看 • 20 天前

Tested out the new Kling AI 2.0 model on Sunday afternoon. Using ChatGPT, I created a bunch of challenging prompts for images in Midjourney and then animated them in Kling 2.0. It's an incredible leap forward for AI motion. I'll comment on some of the tests below.

Tested out the new Kling AI 2.0 model on Sunday afternoon. Using ChatGPT, I created a bunch of challenging prompts for images in Midjourney and then animated them in Kling 2.0. It's an incredible leap forward for AI motion. I'll comment on some of the tests below.

Jason Zada

52,911 次观看 • 1 年前

I built a browser extension with Jev TypeSafe AI that can hide/collapse posts on X based on natural language. It's so fast that it's not noticeable and insanely cheap...this must be the future of "ad blockers" and content firewalls.

I built a browser extension with Jev TypeSafe AI that can hide/collapse posts on X based on natural language. It's so fast that it's not noticeable and insanely cheap...this must be the future of "ad blockers" and content firewalls.

Marcel Pociot 🧪

85,778 次观看 • 13 天前

New Anthropic research: Tracing the thoughts of a large language model. We built a "microscope" to inspect what happens inside AI models and use it to understand Claude’s (often complex and surprising) internal mechanisms.

New Anthropic research: Tracing the thoughts of a large language model. We built a "microscope" to inspect what happens inside AI models and use it to understand Claude’s (often complex and surprising) internal mechanisms.

Anthropic

1,575,235 次观看 • 1 年前

this is unreal f*cking gold for Jev builders 20 repos people are building on Jev right now. browser agents, context tools, trading bots, even a drone 1. JEV-Ultrafast - a fast browser agent ↳ 2. Fast-JEV-Compaction - context compression ↳ 3. JSON-Render - generative UI ↳ 4. Typesafe-MCP - use Jev with any client ↳ 5. JEV-MCP - a judgment toolkit ↳ 6. Semdecide - a classifier that lives in your CLI ↳ 7. JEV-Codex-Router - routes each task to the right model ↳ 8. Winnow - garbage collection for your context ↳ 9. JEV-Review - code review triage ↳ 10. Blink - a repo navigator ↳ 11. Agent-Desktop - desktop automation ↳ 12. Typesafe-Mario - an agent that plays Super Mario ↳ 13. JEV-Drone - drone control ↳ 14. OneVOneJev - a browser FPS ↳ 15. JEV-Trader - HFT market making ↳ 16. Prism - liquidity signal detection ↳ 17. Neo4Jev - knowledge graph traversal ↳ 18. JEV-Curate - training data screening ↳ 19. Canny - checks whether a task was actually completed ↳ 20. KillMyIdea - scores startup ideas before you build them ↳ pick by what you do: > coding -> JEV-Review, Blink, Canny, JEV-Codex-Router > context -> Fast-JEV-Compaction, Winnow > automation -> JEV-Ultrafast, Agent-Desktop > clients and tools -> Typesafe-MCP, JEV-MCP, Semdecide > UI -> JSON-Render > trading -> JEV-Trader, Prism > data -> Neo4Jev, JEV-Curate > founders -> KillMyIdea > just for fun -> Typesafe-Mario, OneVOneJev, JEV-Drone grab the one closest to your job and ship something on top of it this week

this is unreal f*cking gold for Jev builders 20 repos people are building on Jev right now. browser agents, context tools, trading bots, even a drone 1. JEV-Ultrafast - a fast browser agent ↳ 2. Fast-JEV-Compaction - context compression ↳ 3. JSON-Render - generative UI ↳ 4. Typesafe-MCP - use Jev with any client ↳ 5. JEV-MCP - a judgment toolkit ↳ 6. Semdecide - a classifier that lives in your CLI ↳ 7. JEV-Codex-Router - routes each task to the right model ↳ 8. Winnow - garbage collection for your context ↳ 9. JEV-Review - code review triage ↳ 10. Blink - a repo navigator ↳ 11. Agent-Desktop - desktop automation ↳ 12. Typesafe-Mario - an agent that plays Super Mario ↳ 13. JEV-Drone - drone control ↳ 14. OneVOneJev - a browser FPS ↳ 15. JEV-Trader - HFT market making ↳ 16. Prism - liquidity signal detection ↳ 17. Neo4Jev - knowledge graph traversal ↳ 18. JEV-Curate - training data screening ↳ 19. Canny - checks whether a task was actually completed ↳ 20. KillMyIdea - scores startup ideas before you build them ↳ pick by what you do: > coding -> JEV-Review, Blink, Canny, JEV-Codex-Router > context -> Fast-JEV-Compaction, Winnow > automation -> JEV-Ultrafast, Agent-Desktop > clients and tools -> Typesafe-MCP, JEV-MCP, Semdecide > UI -> JSON-Render > trading -> JEV-Trader, Prism > data -> Neo4Jev, JEV-Curate > founders -> KillMyIdea > just for fun -> Typesafe-Mario, OneVOneJev, JEV-Drone grab the one closest to your job and ship something on top of it this week

Mr. Buzzoni

28,799 次观看 • 5 天前

this is f*cking gold 20 GitHub repos with 500K+ combined stars that will level up your JEV workflow AGENTS > jev-ultrafast: Jev picks every click and DOM target, a small LLM only types > hermes-jev-skills: routing, memory, compaction and skill picks in one pack > typesafe-computer-use: OCR reads your Mac screen, Jev picks the next click MEMORY > fast-jev-compaction: scores every tool call keep, truncate or drop instead of summarizing > jevmem: project memory for Claude Code, Cursor and Codex, updated every turn > jev-second-brain: your Obsidian vault, Jev judges which notes duplicate, revise or contradict SAFETY > jev-guard: a gate before every tool call, Jev scores the risk, you set allow, ask or deny TOOLS > skills: the official TypeSafe skill for Claude Code and Codex > system-one-adapter-python: dry-run your questions on an ordinary LLM before you burn a Jev key > jev-mcp: claim checks, screening and ranking as MCP tools > typesafe-mcp: plug Jev into any MCP client > json-render: Vercel's generative UI, where Jev picks the components OPEN MODELS > SemIf-OpenJev: semantic ifs from frozen open models kev: Jev-like models on Qwen that run on your MacBook > laya-mlx: the Laya decision engine on Apple silicon > clm: an open System One model with Choice, Noul and Score > jevlike: train your own Jev-like model TRADING > jev-trader: one buy or sell decision per Monad block START HERE > awesome-jev: the biggest map of everything built on Jev > awesome-jev-by-typesafe: use cases, patterns and starter code bookmark it before your next build

this is f*cking gold 20 GitHub repos with 500K+ combined stars that will level up your JEV workflow AGENTS > jev-ultrafast: Jev picks every click and DOM target, a small LLM only types > hermes-jev-skills: routing, memory, compaction and skill picks in one pack > typesafe-computer-use: OCR reads your Mac screen, Jev picks the next click MEMORY > fast-jev-compaction: scores every tool call keep, truncate or drop instead of summarizing > jevmem: project memory for Claude Code, Cursor and Codex, updated every turn > jev-second-brain: your Obsidian vault, Jev judges which notes duplicate, revise or contradict SAFETY > jev-guard: a gate before every tool call, Jev scores the risk, you set allow, ask or deny TOOLS > skills: the official TypeSafe skill for Claude Code and Codex > system-one-adapter-python: dry-run your questions on an ordinary LLM before you burn a Jev key > jev-mcp: claim checks, screening and ranking as MCP tools > typesafe-mcp: plug Jev into any MCP client > json-render: Vercel's generative UI, where Jev picks the components OPEN MODELS > SemIf-OpenJev: semantic ifs from frozen open models kev: Jev-like models on Qwen that run on your MacBook > laya-mlx: the Laya decision engine on Apple silicon > clm: an open System One model with Choice, Noul and Score > jevlike: train your own Jev-like model TRADING > jev-trader: one buy or sell decision per Monad block START HERE > awesome-jev: the biggest map of everything built on Jev > awesome-jev-by-typesafe: use cases, patterns and starter code bookmark it before your next build

NO1ennn

18,445 次观看 • 2 天前

Adobe (Adobe Video) showcases their new Adobe Firefly video model in Premiere Pro. Their demo video includes third party integrations with Runway, Pika, and OpenAI’s Sora model. A more robust UI for editing and creating with generative tools is very exciting!

Adobe (Adobe Video) showcases their new Adobe Firefly video model in Premiere Pro. Their demo video includes third party integrations with Runway, Pika, and OpenAI’s Sora model. A more robust UI for editing and creating with generative tools is very exciting!

William Lamkin

67,676 次观看 • 2 年前

OpenAI Co-founder Andrej Karpathy explains the new computing paradigm: "We're entering a new computing paradigm with large language models acting like CPUs, using tokens instead of bytes, and having a context window instead of RAM. This is the Large Language Model OS (LMOS)"

OpenAI Co-founder Andrej Karpathy explains the new computing paradigm: "We're entering a new computing paradigm with large language models acting like CPUs, using tokens instead of bytes, and having a context window instead of RAM. This is the Large Language Model OS (LMOS)"

Haider.

552,459 次观看 • 2 年前

this is f*cking gold 12 open-source repos that plug Jev into real AI work, 550.7k stars combined Jev decides, your LLM writes. these repos are where that split already runs: agents > browser-use/jev-ultrafast (~20.3k): Jev picks the next action + DOM element, a small LLM only types. Zürich to London flights in ~7s > awlevin/typesafe-computer-use (~978): macOS computer use, OCR reads the screen, Jev picks the next click local decision models > jaredpalmer/kev (~7.1k): Jev-like models on Qwen, same /v1/systemone wire format > mizorewww/laya-mlx (~6.4k): Laya, the main open Jev-style engine, running on Apple silicon > TheoLeeCJ/SemIf-OpenJev (~4.3k): local semantic ifs from frozen open models, not a TypeSafe project > contrastive-lm/clm (~1.3k): open System One model with a Choice / Noul / Score API > vinnylarouge/jevlike (~1.3k): community trainer and tooling for your own Jev-like model context + skills > tamaratran/fast-jev-compaction (~6.9k): Claude Code plugin, Jev keeps, drops or truncates tool results instead of summarizing context > typesafe-ai/skills (~2.2k): official TypeSafe skill for Claude Code and Codex trading > jarrodwatts/jev-trader (~2.4k): one Jev buy/sell decision per Monad block catalogs > yibie/awesome-jev (~1.7k): the biggest map of Jev projects and discussions > Anil-matcha/awesome-jev-by-typesafe (~851): use cases, patterns and starter code start with jev-ultrafast

this is f*cking gold 12 open-source repos that plug Jev into real AI work, 550.7k stars combined Jev decides, your LLM writes. these repos are where that split already runs: agents > browser-use/jev-ultrafast (~20.3k): Jev picks the next action + DOM element, a small LLM only types. Zürich to London flights in ~7s > awlevin/typesafe-computer-use (~978): macOS computer use, OCR reads the screen, Jev picks the next click local decision models > jaredpalmer/kev (~7.1k): Jev-like models on Qwen, same /v1/systemone wire format > mizorewww/laya-mlx (~6.4k): Laya, the main open Jev-style engine, running on Apple silicon > TheoLeeCJ/SemIf-OpenJev (~4.3k): local semantic ifs from frozen open models, not a TypeSafe project > contrastive-lm/clm (~1.3k): open System One model with a Choice / Noul / Score API > vinnylarouge/jevlike (~1.3k): community trainer and tooling for your own Jev-like model context + skills > tamaratran/fast-jev-compaction (~6.9k): Claude Code plugin, Jev keeps, drops or truncates tool results instead of summarizing context > typesafe-ai/skills (~2.2k): official TypeSafe skill for Claude Code and Codex trading > jarrodwatts/jev-trader (~2.4k): one Jev buy/sell decision per Monad block catalogs > yibie/awesome-jev (~1.7k): the biggest map of Jev projects and discussions > Anil-matcha/awesome-jev-by-typesafe (~851): use cases, patterns and starter code start with jev-ultrafast

NO1ennn

38,564 次观看 • 4 天前

Will the new Hargeisa terminal building have a design like this? A modern, spacious terminal would be a huge step forward creating room for more shops, better passenger experience, and the capacity to attract more airlines and travelers to Hargeisa. #Somaliland #HornOfAfrica

Will the new Hargeisa terminal building have a design like this? A modern, spacious terminal would be a huge step forward creating room for more shops, better passenger experience, and the capacity to attract more airlines and travelers to Hargeisa. #Somaliland #HornOfAfrica

David Green

41,308 次观看 • 6 个月前

I've made a ton of money helping companies implement LLM-as-a-judge evaluations. LLM Judges provide a ton of value. But the hard part is choosing the model to implement the judge. • The family of GPT-5 models is very good, but slow and expensive. • Models like Gemma and Phi are fast and cheap, but not that good. Most of the time, you can only run a percentage of your traffic through the model (otherwise it would be too expensive and slow). But now, there's a better strategy.

I've made a ton of money helping companies implement LLM-as-a-judge evaluations. LLM Judges provide a ton of value. But the hard part is choosing the model to implement the judge. • The family of GPT-5 models is very good, but slow and expensive. • Models like Gemma and Phi are fast and cheap, but not that good. Most of the time, you can only run a percentage of your traffic through the model (otherwise it would be too expensive and slow). But now, there's a better strategy.

Santiago

29,970 次观看 • 5 个月前

Today, Generative AI takes its next big step forward. Introducing Gen-1: a new AI model that uses language and images to generate new videos out of existing ones. Sign up for early research access:

Today, Generative AI takes its next big step forward. Introducing Gen-1: a new AI model that uses language and images to generate new videos out of existing ones. Sign up for early research access:

Runway

2,480,958 次观看 • 3 年前

Happy #screenshotsaturday! I've been busy working on a new build mode for Automation Station. Added a new camera system, build laser, belt placement system, UI, and a ton of other little bits and bobs. Finally feels like its all coming together! #madewithunity #indiedev

Happy #screenshotsaturday! I've been busy working on a new build mode for Automation Station. Added a new camera system, build laser, belt placement system, UI, and a ton of other little bits and bobs. Finally feels like its all coming together! #madewithunity #indiedev

Scott Daley

145,580 次观看 • 3 年前

Open models are closing the intelligence gap, says ollama's Jeffrey Morgan. That opens up a new opportunity for founders: coordinating fast, cheap models to solve more complex problems. “We’re maybe less than three months behind between the frontier closed models and the open models. But the next problem to solve is extreme efficiency.” “They’re good enough for 80% of the tasks, they’re really fast and they’re ultra cheap.” “That class of models, in my mind, will be the first ones that come down to this idea of the unlimited tokens.” “Being able to coordinate these flash models together to do different tasks can also yield great results that a bigger model can.”

Open models are closing the intelligence gap, says ollama's Jeffrey Morgan. That opens up a new opportunity for founders: coordinating fast, cheap models to solve more complex problems. “We’re maybe less than three months behind between the frontier closed models and the open models. But the next problem to solve is extreme efficiency.” “They’re good enough for 80% of the tasks, they’re really fast and they’re ultra cheap.” “That class of models, in my mind, will be the first ones that come down to this idea of the unlimited tokens.” “Being able to coordinate these flash models together to do different tasks can also yield great results that a bigger model can.”

Y Combinator

57,458 次观看 • 26 天前

glm fast mode is my new daily driver for 9/10 tasks where i need to iterate fast. fast, cheap, and imo best bang for buck this is why you shouldn't lock into single model agents, you leave alpha on table given the wide array of options out now.

glm fast mode is my new daily driver for 9/10 tasks where i need to iterate fast. fast, cheap, and imo best bang for buck this is why you shouldn't lock into single model agents, you leave alpha on table given the wide array of options out now.

Saoud Rizwan

19,234 次观看 • 2 个月前

OpenAI just dropped a completely new kind of model gpt-realtime-translate takes in speech audio from any language and outputs speech in your target language LLMs are great, but you need specialized models for specialized use cases We're running this on our smart glasses

OpenAI just dropped a completely new kind of model gpt-realtime-translate takes in speech audio from any language and outputs speech in your target language LLMs are great, but you need specialized models for specialized use cases We're running this on our smart glasses

cayden 凯登

102,302 次观看 • 4 个月前