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。

🎮 This entire Avo Lawn game was built with Muse Spark 1.2 + Muse Code. 🥑 Now it’s your turn—use Muse Spark 1.2 to build your own game and see what you can create. To play: Check out our blog post:

Zi Lin

1,153 subscribers

42,871 次观看 • 1 个月前 •via X (Twitter)

科学技术教育游戏

Anya Rossi• Live Now

Private livecam show

9 条评论

Claire Zhou 的头像

Claire Zhou1 个月前

so much fun!

Pete 的头像

Pete1 个月前

What looks to be a clone of a very popular game? 😬😬😬 maybe run past legal

404 Opinions 的头像

404 Opinions1 个月前

built a game with muse spark 1.2 what they meant: we finally found a way to make you pay for code that writes itself

Fahad 的头像

Fahad1 个月前

AVO LAWN DEFENDED! You survived the Guac-pocalypse!

阿北的 Agent 周末的头像

阿北的 Agent 周末1 个月前

用AI做游戏现在这么顺了？我得去试试这个Muse Spark，看能不能搞个小demo出来，哈哈。

Gargeya 的头像

Gargeya1 个月前

I am facing a muse code installation problem on my mac. Says file not found?

RIDER SKETCH 的头像

RIDER SKETCH1 个月前

Epic game!!!!

Ömer Hamid Kamışlı 🇹🇷 的头像

Ömer Hamid Kamışlı 🇹🇷1 个月前

I love 🥑

AI Mastery Guide 的头像

AI Mastery Guide1 个月前

A full tower defense game built entirely by an agent is wild to see.

相关视频

Power user Muse feature - custom connectors 🔧. Muse has tons of connectors for popular services built in. Even better, Muse can write its own software and run it in the VM you and your Muse share in the cloud. So you can connect Muse to any service with an API.

Power user Muse feature - custom connectors 🔧. Muse has tons of connectors for popular services built in. Even better, Muse can write its own software and run it in the VM you and your Muse share in the cloud. So you can connect Muse to any service with an API.

David Singleton

152,282 次观看 • 13 天前

🚨 Announcing Smart Model Router - Create Your Own Custom Router To Route To Your Favorite LLM - Route to GPT Sol, Muse Spark, Grok 4.5 and Fable - Optimize for cost or performance - Use Fable only for hard coding Once you create a router, you can use it on our Chat, Agent or in an API! Coming on Monday - Support for all CLI clients including Code, Claude Code and others

🚨 Announcing Smart Model Router - Create Your Own Custom Router To Route To Your Favorite LLM - Route to GPT Sol, Muse Spark, Grok 4.5 and Fable - Optimize for cost or performance - Use Fable only for hard coding Once you create a router, you can use it on our Chat, Agent or in an API! Coming on Monday - Support for all CLI clients including Code, Claude Code and others

Bindu Reddy

2,572,380 次观看 • 2 个月前

This beautiful presentation is by Muse 1.2. It used gpt-image-v2 to create the images by itself. I told it to make a history page from Llama to Muse 1.2, and it did a great job. Alexandr Wang , you guys created magic with agentic tasks. I'm now waiting for the big model from you guys.

This beautiful presentation is by Muse 1.2. It used gpt-image-v2 to create the images by itself. I told it to make a history page from Llama to Muse 1.2, and it did a great job. Alexandr Wang , you guys created magic with agentic tasks. I'm now waiting for the big model from you guys.

Chetaslua

17,158 次观看 • 1 个月前

Did you know Muse can do this? Generative sequencing, FM, and diffusion delay working together to create evolving bell patterns that just keep going… ⚡ What ideas does this spark?

Did you know Muse can do this? Generative sequencing, FM, and diffusion delay working together to create evolving bell patterns that just keep going… ⚡ What ideas does this spark?

Moog Synthesizers

11,499 次观看 • 2 个月前

1/ today we're rolling out Muse, our new personal ai assistant. Muse is always-on, wicked fast, can use a browser, connect to your apps, and is designed to be secure. try it now:

1/ today we're rolling out Muse, our new personal ai assistant. Muse is always-on, wicked fast, can use a browser, connect to your apps, and is designed to be secure. try it now:

Alexandr Wang

12,707,370 次观看 • 17 天前

LOOK AT THIS! You can connect Muse with Unusual Whales. See how to build the connector to Unusual Whales API. This is a game changer. Join here:

LOOK AT THIS! You can connect Muse with Unusual Whales. See how to build the connector to Unusual Whales API. This is a game changer. Join here:

unusual_whales

153,137 次观看 • 3 天前

Double Giveaway Time! Here is your chance to win a 33VIP Pass or a Muse Frame 21'5" Gold frame! What you have to do: * Like this post * RT this post * Follow Muse Frame and 33Family * Mention the artist or show the artwork you love to see on a Muse Frame ⬇️ Rules apply

Double Giveaway Time! Here is your chance to win a 33VIP Pass or a Muse Frame 21'5" Gold frame! What you have to do: * Like this post * RT this post * Follow Muse Frame and 33Family * Mention the artist or show the artwork you love to see on a Muse Frame ⬇️ Rules apply

33Family

13,274 次观看 • 3 年前

MUSE FEATURE ALERT: you can video chat with your @muse coming soon! it talks back in real time, and you get to prompt exactly how it sounds! (iphone screen record doesn’t record the sound so you’ll have to try it yourself with your own muse to hear the voice)

MUSE FEATURE ALERT: you can video chat with your @muse coming soon! it talks back in real time, and you get to prompt exactly how it sounds! (iphone screen record doesn’t record the sound so you’ll have to try it yourself with your own muse to hear the voice)

Alexandr Wang

134,696 次观看 • 1 天前

Muse Spark 1.2 supports a broad range of multimodal tasks, from turning visuals into working code to translating perception into physical action. It also brings robust audio-visual understanding to enable video-heavy workflows common in real-world enterprise use. Today, we’re sharing new evals and demos that illustrate the breadth of the model’s visual understanding and reasoning capabilities. Let’s start with a demo that shows how Muse Spark parses multimodal observations and calls tools to guide a robot to navigate in an unstructured environment to find a rubber duck. 🧵👇

Muse Spark 1.2 supports a broad range of multimodal tasks, from turning visuals into working code to translating perception into physical action. It also brings robust audio-visual understanding to enable video-heavy workflows common in real-world enterprise use. Today, we’re sharing new evals and demos that illustrate the breadth of the model’s visual understanding and reasoning capabilities. Let’s start with a demo that shows how Muse Spark parses multimodal observations and calls tools to guide a robot to navigate in an unstructured environment to find a rubber duck. 🧵👇

AI at Meta

57,402 次观看 • 1 个月前

gemini 3.7 flash vs deepseek v4 pro 0813 vs muse spark 1.2 – on voxel city dioramas three models each built three crossy road-style 3d scenes – a construction site, a nyc intersection, a river with a drawbridge – as single self-contained html files the setup: Nous Research's hermes agent cli on OpenRouter, three.js skills preloaded, identical prompts per scene tasks: 1. construction site – tower crane on a working lift loop, paver laying fresh road, roller compacting it behind 2. nyc crossing – four-way intersection with a traffic light state machine, queuing cars, pedestrians crossing on the walk signal 3. river drawbridge – double-leaf bascule that lifts for tall boats, cars queuing at the barriers, animated water every scene: Three.js r185, box geometry only, a locked 20-color palette, four camera presets, and a day/night mode with bloom. one file, no build step, no assets models: Google DeepMind gemini 3.7 flash, DeepSeek v4 pro 0813, AI at Meta muse spark 1.2 muse and gemini finished every scene in two to three minutes. deepseek took 15 to 41 minutes per scene - build time, all three scenes #1 gemini 3.7 flash – 6m 43s #2 muse spark 1.2 – 7m 20s #3 deepseek v4 pro – 91m 25s - total tokens #1 muse spark 1.2 – 440,279 #2 gemini 3.7 flash – 713,855 #3 deepseek v4 pro – 20,957,568 - total price #1 muse spark 1.2 – $0.53 #2 gemini 3.7 flash – $0.56 #3 deepseek v4 pro – $4.57 - agent calls across the three builds #1 muse spark 1.2 – 12 #2 gemini 3.7 flash – 18 #3 deepseek v4 pro – 143 observations: • muse won two of the three scenes on looks with the smallest files in the test – 887 to 1,042 lines against gemini's 1,934 to 2,377. cheapest, fastest to a good frame, and shortest turned out to be the same column • deepseek burned 20.96m tokens – 29x gemini, 48x muse – across 143 agent calls. prompt caching is the only reason that cost $4.57: the cache discount absorbed roughly $30 of resent context • gemini was the only model whose files needed zero fixes to render – and the only one whose night mode is cosmetic. the sky never darkens and one camera button does nothing. clean code for a scene it never looked at follow thehype. for 24/7 ai news, analysis and breakdowns

gemini 3.7 flash vs deepseek v4 pro 0813 vs muse spark 1.2 – on voxel city dioramas three models each built three crossy road-style 3d scenes – a construction site, a nyc intersection, a river with a drawbridge – as single self-contained html files the setup: Nous Research's hermes agent cli on OpenRouter, three.js skills preloaded, identical prompts per scene tasks: 1. construction site – tower crane on a working lift loop, paver laying fresh road, roller compacting it behind 2. nyc crossing – four-way intersection with a traffic light state machine, queuing cars, pedestrians crossing on the walk signal 3. river drawbridge – double-leaf bascule that lifts for tall boats, cars queuing at the barriers, animated water every scene: Three.js r185, box geometry only, a locked 20-color palette, four camera presets, and a day/night mode with bloom. one file, no build step, no assets models: Google DeepMind gemini 3.7 flash, DeepSeek v4 pro 0813, AI at Meta muse spark 1.2 muse and gemini finished every scene in two to three minutes. deepseek took 15 to 41 minutes per scene - build time, all three scenes #1 gemini 3.7 flash – 6m 43s #2 muse spark 1.2 – 7m 20s #3 deepseek v4 pro – 91m 25s - total tokens #1 muse spark 1.2 – 440,279 #2 gemini 3.7 flash – 713,855 #3 deepseek v4 pro – 20,957,568 - total price #1 muse spark 1.2 – $0.53 #2 gemini 3.7 flash – $0.56 #3 deepseek v4 pro – $4.57 - agent calls across the three builds #1 muse spark 1.2 – 12 #2 gemini 3.7 flash – 18 #3 deepseek v4 pro – 143 observations: • muse won two of the three scenes on looks with the smallest files in the test – 887 to 1,042 lines against gemini's 1,934 to 2,377. cheapest, fastest to a good frame, and shortest turned out to be the same column • deepseek burned 20.96m tokens – 29x gemini, 48x muse – across 143 agent calls. prompt caching is the only reason that cost $4.57: the cache discount absorbed roughly $30 of resent context • gemini was the only model whose files needed zero fixes to render – and the only one whose night mode is cosmetic. the sky never darkens and one camera button does nothing. clean code for a scene it never looked at follow thehype. for 24/7 ai news, analysis and breakdowns

thehype.

29,033 次观看 • 1 个月前

Meet Pumpkin, my own personal Muse agent. It actually does tasks instead of telling me how to do them. You can build your own on the Muse app. Businesses and products shown are AI-generated suggestions, not sponsored, endorsed by, or affiliated with Meta.

Meet Pumpkin, my own personal Muse agent. It actually does tasks instead of telling me how to do them. You can build your own on the Muse app. Businesses and products shown are AI-generated suggestions, not sponsored, endorsed by, or affiliated with Meta.

Ryan Serhant

24,187 次观看 • 16 天前

1/ muse code is out of beta. launching with an sdk in developer preview to build your own agents on top of it and rolling out monthly subscription plans. copy-paste into your terminal: curl -fsSL | bash

1/ muse code is out of beta. launching with an sdk in developer preview to build your own agents on top of it and rolling out monthly subscription plans. copy-paste into your terminal: curl -fsSL | bash

Alexandr Wang

165,285 次观看 • 25 天前

The price of frontier AI just hit zero. Three times in one week. > OpenAI: GPT-5.6 Luna free and unlimited in ChatGPT. No caps, no card: > MonkeyCode: 30M tokens/day, resets daily. DeepSeek V4 Flash, Qwen, GLM, Kimi, MiniMax. Browser-based: > Meta Muse Code: $1.25 per million input tokens. Terminal agent, Muse Spark 1.2. macOS, Linux: The barrier stopped being price. Now it's knowing where to look.

The price of frontier AI just hit zero. Three times in one week. > OpenAI: GPT-5.6 Luna free and unlimited in ChatGPT. No caps, no card: > MonkeyCode: 30M tokens/day, resets daily. DeepSeek V4 Flash, Qwen, GLM, Kimi, MiniMax. Browser-based: > Meta Muse Code: $1.25 per million input tokens. Terminal agent, Muse Spark 1.2. macOS, Linux: The barrier stopped being price. Now it's knowing where to look.

ＺＥＦＩ

38,420 次观看 • 1 个月前

I pay for Muse Code but didn't want to live in a terminal. On Windows it's WSL-only. So I built Helicon: an open-source desktop app for the actual Muse CLI. • uses your existing muse login, no API key • talks to muse serve over MSP, so Muse stays the agent • resumes sessions you started in the terminal • projects, diffs, approvals, cost in one window • signed Windows installer + universal macOS build Same harness. Real UI. Unofficial, not affiliated with Meta.

I pay for Muse Code but didn't want to live in a terminal. On Windows it's WSL-only. So I built Helicon: an open-source desktop app for the actual Muse CLI. • uses your existing muse login, no API key • talks to muse serve over MSP, so Muse stays the agent • resumes sessions you started in the terminal • projects, diffs, approvals, cost in one window • signed Windows installer + universal macOS build Same harness. Real UI. Unofficial, not affiliated with Meta.

harjot.co

70,146 次观看 • 9 天前

Google just made Gemini Spark much more powerful 🔥 Spark can now use Chrome to handle complex task. It can use your logged-in accounts and saved passwords, while handing sensitive actions like payments back to you. Video credit: Google Blog

Google just made Gemini Spark much more powerful 🔥 Spark can now use Chrome to handle complex task. It can use your logged-in accounts and saved passwords, while handing sensitive actions like payments back to you. Video credit: Google Blog

AshutoshShrivastava

20,963 次观看 • 1 个月前

What started as a brief to launch Leonardo’s 3D capabilities, quickly turned into our team building a game you can actually play. Watch our latest Creator Breakdown to see how it came to life, and check out the blog to play the game.

What started as a brief to launch Leonardo’s 3D capabilities, quickly turned into our team building a game you can actually play. Watch our latest Creator Breakdown to see how it came to life, and check out the blog to play the game.

Leonardo.Ai

12,024 次观看 • 3 个月前

IP you love. Universe you don't own. Azuki is now on Story Protocol Legacy — now you can pull the IP into Verse8 and turn it into your own open world game. See it in action. Pull the IP. Build. Own what you create.

IP you love. Universe you don't own. Azuki is now on Story Protocol Legacy — now you can pull the IP into Verse8 and turn it into your own open world game. See it in action. Pull the IP. Build. Own what you create.

Verse 8 | Why Code, Just Verse 8

12,377 次观看 • 5 个月前

A few weeks ago, I shared a Shopify store I built with v0 that you can explore like a game. People asked how I built it, so I recorded a demo to teach you how to build your own. I'd love to see what you create!

A few weeks ago, I shared a Shopify store I built with v0 that you can explore like a game. People asked how I built it, so I recorded a demo to teach you how to build your own. I'd love to see what you create!

Esteban Suárez

20,371 次观看 • 2 个月前

Our newest game 🔪KILLER TYCOON 🔪 2247-5823-2825 is now live! Wear different Masks to kill targets, buy supercars, build your own helicopter, find awesome secrets and much more! 📷Check it out! Use this code inside the game to get 2x Ingame XP (not FN XP): 5832

Our newest game 🔪KILLER TYCOON 🔪 2247-5823-2825 is now live! Wear different Masks to kill targets, buy supercars, build your own helicopter, find awesome secrets and much more! 📷Check it out! Use this code inside the game to get 2x Ingame XP (not FN XP): 5832

Creative Minds Studios

261,121 次观看 • 2 年前

visionOS 26.2 developer beta added system level support for the Logitech Muse accessory! Now it has its own menu built-in to system settings It’s compatible with all your iPad and non-immersive windows And immediately made this accessory go from useless to perfect!

visionOS 26.2 developer beta added system level support for the Logitech Muse accessory! Now it has its own menu built-in to system settings It’s compatible with all your iPad and non-immersive windows And immediately made this accessory go from useless to perfect!

Brad Lynch

50,706 次观看 • 10 个月前