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。

We turned Qwen3.8-27B into a multimodal decision model. It beat Pokémon FireRed’s elite four and champion with sub-100 ms decisions from live game state. With SGLang’s native /v1/decisions, you can now turn LLMs and VLMs into classification and scoring models. We also added /v1/systemone so Jev-like open models can... show more

SGLang

10,303 subscribers

221,988 次观看 • 1 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

21 条评论

SGLang 的头像

SGLang1 天前

One of the most exciting parts of Pokémon is type matchups and knowing when to attack, switch, or heal. Qwen3.8-27B is a surprisingly good Pokémon player. It cleared the Elite Four and Champion in one go. Full run playback👇

SGLang 的头像

SGLang1 天前

You can now try SGLang’s new decision API with the nightly image. It will also be included in v0.5.21 this Thursday.

BlackwellBoy 的头像

BlackwellBoy1 天前

I wonder if this could help with quicker decision making for my little chits project

Stochastic Cowboy 的头像

Stochastic Cowboy1 天前

Very cool! Will definitely try this out. For the Pokemon demo is there any harness that is tracking game state, or is it purely a loop where the model is presented with the screenshot and outputs an action?

Sakura Yuki 的头像

Sakura Yuki1 天前

Does sub-100 ms include game-state capture, image preprocessing, and VLM prefill, or is it just /v1/decisions server time? That breakdown is the interesting part.

bhavesh 的头像

bhavesh1 天前

awesome! but FireRed is easy :) we should see if models can win truly difficult battles

Day | AI + Software 的头像

Day | AI + Software1 天前

Woahhhh impressive might try out SG Lang for the first time

Trust⭕️ 的头像

Trust⭕️1 天前

Woah

Alan Ma 的头像

Alan Ma23 小时前

goated team

Will 的头像

Will1 天前

Yes! I love it.

Greg Konush (｡◕‿◕｡) 的头像

Greg Konush (｡◕‿◕｡)1 天前

p99 under concurrent load?

Amar Singh 的头像

Amar Singh1 天前

crazy to think what the future of video games are going to be, pokemon is fine but it's going to be impossible to determine if someone is a bot in online games

Hardik Jindal 的头像

Hardik Jindal1 天前

curious if you have added a lora adapter for qwen3.8, similar to kev 27b 🤔

Azeez 的头像

Azeez1 天前

This is so so sick 🔥 FireRed is my favorite Pokemon game (close second Soul Silver)

Shreyas Karnik 的头像

Shreyas Karnik1 天前

really cool!

Bin Chen 的头像

Bin Chen1 天前

can it be used in other task, eg: given two chat history capture, and ask if there is new message?

Jintao Zhang 张晋涛的头像

Jintao Zhang 张晋涛1 天前

🐐

John Rood 的头像

John Rood1 天前

the artifact I want off this run: the decisive turns, the spots where a wrong move loses the battle, and what it picked there. a playthrough is mostly forgiving, so the clear is really a story about the handful of moments that weren't.

季风的头像

季风1 天前

cool！

SocialWatch 的头像

SocialWatch1 天前

This is so cool!

Louis 的头像

Louis23 小时前

cool

相关视频

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

Jev v1.13 dodges rockets with probability calculation 🚀 TypeSafe AI's new non-LLM model returns decisions instead of text so we had it calculate a safe tile every 330 ms while rockets fell and it survived 25 of 26 for under a cent Run Jev via API ->

Jev v1.13 dodges rockets with probability calculation 🚀 TypeSafe AI's new non-LLM model returns decisions instead of text so we had it calculate a safe tile every 330 ms while rockets fell and it survived 25 of 26 for under a cent Run Jev via API ->

atomic.chat

60,458 次观看 • 13 天前

1/ Offline computer-use models are here. Today, one running on our Mac made it all the way to hotel checkout. We ran Qwen3.8-27B from Qwen through Cua Driver. It also turned a flyer into a Calendar event and reconciled receipts. Every model token stayed on the Mac 🧵

1/ Offline computer-use models are here. Today, one running on our Mac made it all the way to hotel checkout. We ran Qwen3.8-27B from Qwen through Cua Driver. It also turned a flyer into a Calendar event and reconciled receipts. Every model token stayed on the Mac 🧵

Francesco

27,540 次观看 • 1 个月前

oh may.. 3D Gaussian Splat is so crazy now last time we need weeks to turn a room into a 3D model.. now with AI 3DGS, you do it in seconds… even zoom into the text and looks perfect give it like 6 months… you can turn a whole city into a full detailed 3D model

oh may.. 3D Gaussian Splat is so crazy now last time we need weeks to turn a room into a 3D model.. now with AI 3DGS, you do it in seconds… even zoom into the text and looks perfect give it like 6 months… you can turn a whole city into a full detailed 3D model

el.cine

143,676 次观看 • 10 个月前

Jev x GPT-6 Astra x H3 Max I created a complex decision making game with Astra. It is about keeping the city on a whale alive with decisions. - GPT 6 Astra designed the world - Jev chose the actions - H3 Max Turbo on fal turned one decision from each round into video All of the Jev decision making and video generations took only 5 minutes for 264 clips

Jev x GPT-6 Astra x H3 Max I created a complex decision making game with Astra. It is about keeping the city on a whale alive with decisions. - GPT 6 Astra designed the world - Jev chose the actions - H3 Max Turbo on fal turned one decision from each round into video All of the Jev decision making and video generations took only 5 minutes for 264 clips

gokaygokay

21,821 次观看 • 12 天前

Procedural models are so fun to work with! You can have so much control over your own models and creations. 💜 Let me know if I should turn this into a plugin... 👀 #RobloxDev #Roblox

Procedural models are so fun to work with! You can have so much control over your own models and creations. 💜 Let me know if I should turn this into a plugin... 👀 #RobloxDev #Roblox

obviouslypurple

157,083 次观看 • 4 个月前

Dave McMenamin on why the NBA scheduled a 3 PM game for Opening Night: "I've talked to people around the league today and they're like we could sense the excitement for the NBA right now. So let's experiment with this thing. They talked with executives at NBC, and it was kind of a joint decision that this is something we can turn into a celebration of the game. It's already a marquee moment for the league. Let's see if we can enhance it and turn it into a major showcase. Maybe down the line, this becomes a tradition for NBA fans...also an added bonus: it's an international game; 3 PM Eastern is prime time viewing in Europe"

Dave McMenamin on why the NBA scheduled a 3 PM game for Opening Night: "I've talked to people around the league today and they're like we could sense the excitement for the NBA right now. So let's experiment with this thing. They talked with executives at NBC, and it was kind of a joint decision that this is something we can turn into a celebration of the game. It's already a marquee moment for the league. Let's see if we can enhance it and turn it into a major showcase. Maybe down the line, this becomes a tradition for NBA fans...also an added bonus: it's an international game; 3 PM Eastern is prime time viewing in Europe"

Oh No He Didn't

307,340 次观看 • 1 个月前

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.

AK

249,798 次观看 • 3 年前

Jev and the System One Model: RLCD, intelligence/$, reliable AI, & the end of chat-first AI TypeSafe AI CEO Diogo Almeida explains why AI can solve extraordinarily hard problems yet still fail to automate basic work, why Jev is built for reliable decisions inside software instead of chat, why TypeSafe rejects public benchmarks and refusals at the API layer, why data and the right task matter more than brute-force compute, how System One Models could reshape coding agents and software, and why even with $1 billion he wouldn’t pre-train a model from scratch.

Jev and the System One Model: RLCD, intelligence/$, reliable AI, & the end of chat-first AI TypeSafe AI CEO Diogo Almeida explains why AI can solve extraordinarily hard problems yet still fail to automate basic work, why Jev is built for reliable decisions inside software instead of chat, why TypeSafe rejects public benchmarks and refusals at the API layer, why data and the right task matter more than brute-force compute, how System One Models could reshape coding agents and software, and why even with $1 billion he wouldn’t pre-train a model from scratch.

Latent.Space

401,288 次观看 • 9 天前

You can now run Qwen3.8-27B in full BF16 on a free Kaggle TPU. - with about 130 tok/s decode, - 10k tok/s prefill, - Native 262k context. - No quantization. - No paid GPU. - Measured on TPU v5e-8 It also exposes an OpenAI-compatible endpoint, so it plugs into Claude Code, Codex, and OpenCode.

You can now run Qwen3.8-27B in full BF16 on a free Kaggle TPU. - with about 130 tok/s decode, - 10k tok/s prefill, - Native 262k context. - No quantization. - No paid GPU. - Measured on TPU v5e-8 It also exposes an OpenAI-compatible endpoint, so it plugs into Claude Code, Codex, and OpenCode.

Md Ismail Šojal 🕷️

50,394 次观看 • 24 天前

Announcing the Open Model Series: a new series on open source AI models, with merve of Hugging Face. Hugging Face is the open model hub: it hosts model weights, datasets, evals, & demo apps, and maintains the open-source libraries (like transformers) used to run and train them. I think of it like GitHub, but for AI models. You can download open models and run them on your own machines. In this series we'll cover what open source and open weight models are, how they work, how to run them yourself, and why they're important. By the way - this video is edited entirely with Claude! I can make a tutorial on how I did it. If there's a question you want answered about open models, leave it in the comments. We will read them all. Episode 1 is out soon.

Announcing the Open Model Series: a new series on open source AI models, with merve of Hugging Face. Hugging Face is the open model hub: it hosts model weights, datasets, evals, & demo apps, and maintains the open-source libraries (like transformers) used to run and train them. I think of it like GitHub, but for AI models. You can download open models and run them on your own machines. In this series we'll cover what open source and open weight models are, how they work, how to run them yourself, and why they're important. By the way - this video is edited entirely with Claude! I can make a tutorial on how I did it. If there's a question you want answered about open models, leave it in the comments. We will read them all. Episode 1 is out soon.

Harper Carroll

30,392 次观看 • 1 个月前

NeoHorse-Jev-4B is now open—a compact model built to turn application states directly into structured decisions and probabilities. 🤖 🏆 Scores 77.70 across six text decision benchmark groups, ranking first among the four open-weight models with complete results in the comparison. ⚡ Prefill-only inference avoids autoregressive answer generation and supports three decision primitives: Choice for action selection, Noul for yes/no judgment, and Score for ordered ratings. 🎮 The same interface can power request routing, tool selection, workflow control, games, robot manipulation, and autonomous-driving simulations. 🖼️ Supports text inputs or a single image combined with text, returning normalized probabilities that applications can use directly. 🛠️ Deploy locally through vLLM, SGLang, Python, CLI, or HTTP. Apache 2.0.

NeoHorse-Jev-4B is now open—a compact model built to turn application states directly into structured decisions and probabilities. 🤖 🏆 Scores 77.70 across six text decision benchmark groups, ranking first among the four open-weight models with complete results in the comparison. ⚡ Prefill-only inference avoids autoregressive answer generation and supports three decision primitives: Choice for action selection, Noul for yes/no judgment, and Score for ordered ratings. 🎮 The same interface can power request routing, tool selection, workflow control, games, robot manipulation, and autonomous-driving simulations. 🖼️ Supports text inputs or a single image combined with text, returning normalized probabilities that applications can use directly. 🛠️ Deploy locally through vLLM, SGLang, Python, CLI, or HTTP. Apache 2.0.

ModelScope

18,748 次观看 • 6 天前

The White House posted that Trump Game clip this morning. I used Grok Bot to turn it into a playable browser game. V1 is live. The idea is simple: kids and young players learn basic investing by running a company inside the game. Lessons, businesses, a team, and a resource loop. Better decisions make the company stronger. Progress saves on the server. More systems coming. Built with Grok Grok Bot.

The White House posted that Trump Game clip this morning. I used Grok Bot to turn it into a playable browser game. V1 is live. The idea is simple: kids and young players learn basic investing by running a company inside the game. Lessons, businesses, a team, and a resource loop. Better decisions make the company stronger. Progress saves on the server. More systems coming. Built with Grok Grok Bot.

As Found

176,472 次观看 • 21 天前

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Santiago

164,162 次观看 • 2 年前

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

Corent’s brain uses TypeSafe AI Jev now. Not to generate the output, to make the decision before the output gets generated. When a request comes into Corent, you don’t need to tell us which model to use. You send the prompt, the workload and the quality level. Then Jev helps us decide what that request actually needs, how confident we are in that decision, and whether we should take the route or fall back to something safer. That matters because every request has different economics. A 2¢ image can tolerate more uncertainty. A $2 video clip cannot. Across 1000+ models, this changes how we route. We can set different confidence requirements depending on the workload, the cost and the quality expected. If the confidence is too low, we stop guessing. Routing was never really a text problem. It was a decision problem. Diogo Almeida and the team did a wonderful job with JEV Get your key at

Corent’s brain uses TypeSafe AI Jev now. Not to generate the output, to make the decision before the output gets generated. When a request comes into Corent, you don’t need to tell us which model to use. You send the prompt, the workload and the quality level. Then Jev helps us decide what that request actually needs, how confident we are in that decision, and whether we should take the route or fall back to something safer. That matters because every request has different economics. A 2¢ image can tolerate more uncertainty. A $2 video clip cannot. Across 1000+ models, this changes how we route. We can set different confidence requirements depending on the workload, the cost and the quality expected. If the confidence is too low, we stop guessing. Routing was never really a text problem. It was a decision problem. Diogo Almeida and the team did a wonderful job with JEV Get your key at

corent

109,541 次观看 • 12 天前

Have you peeped the latest Model Playground update on our serverless inference service? We upgraded our UI so you can test and iterate on models with zero setup. Toggle live updates to see real-time API behavior. Adjust input parameters with full visibility. > Copy-ready requests in Python, TypeScript, cURL, and Gradio > Works across text, vision, image, and audio models > Built on top of the Vercel AI SDK

Have you peeped the latest Model Playground update on our serverless inference service? We upgraded our UI so you can test and iterate on models with zero setup. Toggle live updates to see real-time API behavior. Adjust input parameters with full visibility. > Copy-ready requests in Python, TypeScript, cURL, and Gradio > Works across text, vision, image, and audio models > Built on top of the Vercel AI SDK

Hyperbolic

12,919 次观看 • 1 年前

Introducing a creator—first platform for interactive AI films and games. While world models like Genie 3 showed us real-time generated worlds from prompts, Yoroll takes it further: native video-native interaction designed for storytellers and game makers — turning passive generative video into playable, branching narratives. Turn worlds, characters, and scenes into playable, branching video with choices, QTEs, and persistent state—in minutes. Creator beta is open: #AIGaming #InteractiveVideo #GenerativeAI #Genie3

Introducing a creator—first platform for interactive AI films and games. While world models like Genie 3 showed us real-time generated worlds from prompts, Yoroll takes it further: native video-native interaction designed for storytellers and game makers — turning passive generative video into playable, branching narratives. Turn worlds, characters, and scenes into playable, branching video with choices, QTEs, and persistent state—in minutes. Creator beta is open: #AIGaming #InteractiveVideo #GenerativeAI #Genie3

Yoroll

123,787 次观看 • 8 个月前

we went and saw jackass the other day and tonight when we were doing fireworks it inevitably turned into a “see if you can hit me with a roman candle” with me and one of my nieces lol

we went and saw jackass the other day and tonight when we were doing fireworks it inevitably turned into a “see if you can hit me with a roman candle” with me and one of my nieces lol

Shea Serrano

161,071 次观看 • 2 个月前