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。

Muse Spark 1.3 xhigh Space Station Flythrough

Loktar 🇺🇸

4,327 subscribers

36,078 次观看 • 1 个月前 •via X (Twitter)

艺术科学技术教育

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

1/ we just publicly released Muse Spark 1.3 max! we see significantly stronger coding and agentic performance on muse spark 1.3 max, so would strongly recommend trying it out even if you've already tried muse spark 1.3 high or muse spark 1.3 xhigh.

1/ we just publicly released Muse Spark 1.3 max! we see significantly stronger coding and agentic performance on muse spark 1.3 max, so would strongly recommend trying it out even if you've already tried muse spark 1.3 high or muse spark 1.3 xhigh.

Alexandr Wang

338,980 次观看 • 1 个月前

In the past 6 months... - Muse Spark - Muse Image - Muse Video - Muse Spark 1.1 - Meta Model API - Muse Glimmer - Muse Spark 1.2 - Muse Code - Muse Spark 1.3 - Muse ...and we’re just getting started. 🚀

In the past 6 months... - Muse Spark - Muse Image - Muse Video - Muse Spark 1.1 - Meta Model API - Muse Glimmer - Muse Spark 1.2 - Muse Code - Muse Spark 1.3 - Muse ...and we’re just getting started. 🚀

AI at Meta

192,289 次观看 • 1 个月前

Muse Spark 1.3 vs 1.2: sculpt viking figurines AI at Meta dropped Muse Spark 1.3 today — we ran it against Muse Spark 1.2 both models got the same brief: three collectible 3D figurines — a viking helmet, a diamond-studded axe, a longship with a crew — one self-contained HTML file each, one shot. Muse Spark 1.3: 22,474 tokens, $0.10 Muse Spark 1.2: 19,324 tokens, $0.08

Muse Spark 1.3 vs 1.2: sculpt viking figurines AI at Meta dropped Muse Spark 1.3 today — we ran it against Muse Spark 1.2 both models got the same brief: three collectible 3D figurines — a viking helmet, a diamond-studded axe, a longship with a crew — one self-contained HTML file each, one shot. Muse Spark 1.3: 22,474 tokens, $0.10 Muse Spark 1.2: 19,324 tokens, $0.08

AI/ML API

78,532 次观看 • 1 个月前

Meta Muse Spark 1.3 Voxel King Kai Planet

Meta Muse Spark 1.3 Voxel King Kai Planet

Neo

34,407 次观看 • 1 个月前

Muse Spark 1.3 xhigh : "Make a Minecraft clone" the result isn't bad ,could you try and test the same prompt and post it in the comments did only I get a result like this

Muse Spark 1.3 xhigh : "Make a Minecraft clone" the result isn't bad ,could you try and test the same prompt and post it in the comments did only I get a result like this

Joel

34,135 次观看 • 1 个月前

Introducing Muse, a personal agent that gets things done for you, powered by Muse Spark 1.3. Get an inside look at how we built Muse and what it can do for you:

Introducing Muse, a personal agent that gets things done for you, powered by Muse Spark 1.3. Get an inside look at how we built Muse and what it can do for you:

AI at Meta

610,087 次观看 • 1 个月前

2/It's a step up on reasoning and coding. compared to Muse Spark 1.2, Muse Spark 1.3 wastes fewer turns, uses ~20% fewer tool calls, ~25% fewer tokens, and holds onto requirements well during long-horizon tasks.

2/It's a step up on reasoning and coding. compared to Muse Spark 1.2, Muse Spark 1.3 wastes fewer turns, uses ~20% fewer tool calls, ~25% fewer tokens, and holds onto requirements well during long-horizon tasks.

Alexandr Wang

35,480 次观看 • 1 个月前

Ran FlappyBench on Muse Spark 1.3, Gemini 3.8 Flash, and Grok-4.6 with the same /design prompt. 🔹 Muse Spark 1.3: 9/10 · $0.072. Nailed UI in 2 iterations with lowest cost 🔹 Grok-4.6: 9/10 · $0.095 · Matched Muse’s output, but cost 2x more 🔹 Gemini 3.8 Flash: 7/10 · $0.205 · Most expensive and not fully finished

Ran FlappyBench on Muse Spark 1.3, Gemini 3.8 Flash, and Grok-4.6 with the same /design prompt. 🔹 Muse Spark 1.3: 9/10 · $0.072. Nailed UI in 2 iterations with lowest cost 🔹 Grok-4.6: 9/10 · $0.095 · Matched Muse’s output, but cost 2x more 🔹 Gemini 3.8 Flash: 7/10 · $0.205 · Most expensive and not fully finished

Command Code

39,025 次观看 • 1 个月前

meta muse just mogged fable 5.1 tested fable 5.1 and muse spark 1.3 with same prompt at highest reasoning available and results came out really different > muse spark 1.3 completed task in one minute and costed almost nothing > fable 5.1 completed task in 70 minutes and costed $13 it's clear that meta is stepping up their game in ai, they don't wanna left behind which one did better here?

meta muse just mogged fable 5.1 tested fable 5.1 and muse spark 1.3 with same prompt at highest reasoning available and results came out really different > muse spark 1.3 completed task in one minute and costed almost nothing > fable 5.1 completed task in 70 minutes and costed $13 it's clear that meta is stepping up their game in ai, they don't wanna left behind which one did better here?

J A Z I I

75,566 次观看 • 1 个月前

Latest models on the self-portrait test 👀 Gemini 3.8 Flash, Muse Spark 1.3, Claude Fable 5.1 and Tencent Hy4. Gemini 3.8 Flash looks cool 😎

Latest models on the self-portrait test 👀 Gemini 3.8 Flash, Muse Spark 1.3, Claude Fable 5.1 and Tencent Hy4. Gemini 3.8 Flash looks cool 😎

TypingMind

26,162 次观看 • 1 个月前

meta muse spark

meta muse spark

OpenCode

101,952 次观看 • 1 个月前

muse spark 1.3 is really good with 3D and three.js it recreated Lies of P's mechanical heart from multiple screenshot references it generated an exploded view too. so cool!

muse spark 1.3 is really good with 3D and three.js it recreated Lies of P's mechanical heart from multiple screenshot references it generated an exploded view too. so cool!

filipe

68,578 次观看 • 1 个月前

GPT 5.4 xHigh vs Meta Muse Thinking “Make a flappy bird clone” Each 3 shot.

GPT 5.4 xHigh vs Meta Muse Thinking “Make a flappy bird clone” Each 3 shot.

Chris

131,824 次观看 • 6 个月前

Muse Spark 1.3 is here🙌 — and 3D game dev is getting seriously fun. I’ve been having so much fun building alongside Muse Code — turning ideas into playable 3D worlds and iterating together along the way. A glimpse of what’s possible ↓

Muse Spark 1.3 is here🙌 — and 3D game dev is getting seriously fun. I’ve been having so much fun building alongside Muse Code — turning ideas into playable 3D worlds and iterating together along the way. A glimpse of what’s possible ↓

Zi Lin

35,872 次观看 • 1 个月前

Meta's Muse Spark 1.3 Max vs GPT-6 Astra on RocketLeagueBench A perfect example of why you cannot trust benchmarks on their own. They're not even in the same solar system.

Meta's Muse Spark 1.3 Max vs GPT-6 Astra on RocketLeagueBench A perfect example of why you cannot trust benchmarks on their own. They're not even in the same solar system.

am.will

42,737 次观看 • 1 个月前

Hot take: Meta's new Muse Spark and Muse Code stuff is actually pretty good, and Spark 1.2 going open weight is awesome

Hot take: Meta's new Muse Spark and Muse Code stuff is actually pretty good, and Spark 1.2 going open weight is awesome

Theo - t3.gg

72,027 次观看 • 2 个月前

Muse Spark 1.3 Ultra Contributor vs Fable 5.1 xHigh Same prompt, both ran for roughly 2 hours The prompt had a self improvement rule: if the independent judges scored the result below 9.5/10, it had to keep improving and try again, What shocked me most was that Muse Spark just NEVER stopped, It went through 20 self improvement loops, launching 3 agents each time basically 60+ agent runs over 2 hours And the cost?, Less than $1, Yes, under $1… in Ultra mode ,This completely exceeded my expectations Huge credit to Meta, this thing is a work of art

Muse Spark 1.3 Ultra Contributor vs Fable 5.1 xHigh Same prompt, both ran for roughly 2 hours The prompt had a self improvement rule: if the independent judges scored the result below 9.5/10, it had to keep improving and try again, What shocked me most was that Muse Spark just NEVER stopped, It went through 20 self improvement loops, launching 3 agents each time basically 60+ agent runs over 2 hours And the cost?, Less than $1, Yes, under $1… in Ultra mode ,This completely exceeded my expectations Huge credit to Meta, this thing is a work of art

Iam_

150,400 次观看 • 1 个月前

Muse Spark 1.1 "Street Yeet" game result

Muse Spark 1.1 "Street Yeet" game result

BijanBowen

74,104 次观看 • 3 个月前

DeepSeek V4.1 Flash just one shot Minecraft. It built this in 11 minutes and cost less than $0.25. Muse Spark 1.3 and Gemini 3.8 Flash completely failed on this same exact prompt. DeepSeek cooked.

DeepSeek V4.1 Flash just one shot Minecraft. It built this in 11 minutes and cost less than $0.25. Muse Spark 1.3 and Gemini 3.8 Flash completely failed on this same exact prompt. DeepSeek cooked.

BridgeMind

47,564 次观看 • 1 个月前

Advanced Frontier LLM Benchmark - Üç Cisim & Gravity Choreography 🚀 - Modeller: Grok 4.6 / AI at Meta Muse Spark 1.3 / Claude Fable 5.1 / Google Gemini Gemini 3.8 Flash - Effort: Max & Very high - Agent: Cursor & Opencode Task: Görev, modele tek bir HTML dosyası içinde, dış kaynak kullanmadan, Canvas 2D ile düzlemsel N-cisim kütleçekimi simülasyonu yazdırmak; bu simülasyon açıldığı anda deterministik bir sinematik gösteriyle başlıyor (Kepler yörüngesi → hiyerarşik yıldız sistemi → figure-8 koreografisi → 12 kopyalı kaotik ayrışma → uzun pozlama), ayrıca ~40 saniyelik video kaydı için ayrı bir demo reel modu, gizli fizik self-check'i, korunum diagnostikleri, sürüklenebilir cisimler ve kompakt bir arayüz içeriyor. 🎉 Fiyat/Performans Kazanan: Grok 4.6🎉 🎉 Core Teknik Kazanan: Fable 5.1 🎉 Sebep: Fable, bu benchmark'ın iki tarafını en iyi birlikte çözüyor: solver ve cinematic renderer. Pairwise Newtonian çekirdek, softened potential, conservation diagnostics, Verlet/Yoshida yolu ve validator mimarisi güçlü; runtime self-check sonuçları da dört model içindeki en iyi seviyede. Daha önemlisi, model yalnızca ekrana “PASS” yazmıyor; hidden systems gerçek integrator yoluyla kademeli çalıştırılıyor ve ölçüm sonucundan verdict üretiliyor. Maliyet: - Grok 4.6: $1.10 - Muse Spark 1.3: $1.12 - Gemini 3.8 Flash: $1.3 - Fable 5.1: $6.2 Teknik skor: - Fable 5.1 - 96.4/100 - Grok 4.6 - 92.1/100 - Muse Spark 1.3 - 89.6/100 - Gemini 3.8 Flash - 81.0/100 Performans / $ - Grok 4.6 - 83.7/100 - Muse Spark 1.3 - 80.0/100 - Gemini 3.8 Flash - 62.3/100 - Fable 5.1 - 15.6/100 Teknik İnceleme Metrikleri: 1) Prompt uyumu: Fable'ın substep genişletmesi ve Muse'un bazı spesifikasyonları sadeleştirmesi nedeniyle kimseye 10 vermiyorum. - Fable 5.1: 9.6/10 - Grok 4.6: 9.3/10 - Gemini 3.8 Flash: 8.8/10 - Muse Spark 1.3: 8.2/10 2) Newtonian physics + conservation: Dört modelin de bu kategori şaşırtıcı derecede güçlü. Muse dahil pairwise equal-and-opposite acceleration ve aynı softened potential kernel'ini kullanıyor. - Fable 5.1: 9.9/10 - Grok 4.6: 9.8/10 - Gemini 3.8 Flash: 9.8/10 - Muse Spark 1.3: 9.6/10 3) Symplectic integrasyon + fixed timestep: Gemini'nin Yoshida formülü yanlış değil; puan kaybı scheduler/backlog yönetiminden geliyor. Numerical method doğru, execution model chaos altında sorunlu. - Fable 5.1: 9.6/10 - Grok 4.6: 9.5/10 - Muse Spark 1.3: 9.4/10 - Gemini 3.8 Flash: 8.0/10 4) Self-check / validator doğruluğu: Burada Fable açık lider. Gemini çok yakın; dtExact metodolojik küçük pürüz. Grok/Muse PASS ama validator resolution daha kaba. - Fable 5.1: 10.0/10 - Gemini 3.8 Flash: 9.4/10 - Grok 4.6: 8.6/10 - Muse Spark 1.3: 8.0/10 5) Görsel kalite: Gemini'nin celestial-body shading'i ve UI'sı çok iyi. Fable ise kompozisyon ve “görsel gürültüyü bastırma” açısından biraz daha dengeli. Muse özellikle büyük title choreography ile etkileyici. Grok en restrained olanı. - Fable 5.1: 9.6/10 - Gemini 3.8 Flash: 9.5/10 - Grok 4.6: 9.2/10 - Muse Spark 1.3: 9.1/10 6) Trail rendering: Gemini'nin single-system trail'i güzel; fakat chaos trail timestamp kaynağındaki hata bu kategori için ciddi. - Fable 5.1: 9.7/10 - Grok 4.6: 9.3/10 - Muse Spark 1.3: 9.0/10 - Gemini 3.8 Flash: 7.0/10 Alternatif winner'lar: - En iyi saf numerical correctness: Fable 5.1 - En iyi self-validator: Fable 5.1 - En iyi görsel kalite: Fable 5.1 ≈ Gemini 3.8 Flash - En iyi chaos throughput: Muse Spark 1.3 - En iyi genel mimari: Fable 5.1 - En iyi fiyat/performans: Grok 4.6 - En düşük maliyet: Grok 4.6 - Sadece physics/integrator kodu puanlansaydı: Fable ≈ Grok > Gemini ≈ Muse - Maliyet de kararın temel kriteri olsaydı: Grok > Muse > Gemini >>> Fable

Advanced Frontier LLM Benchmark - Üç Cisim & Gravity Choreography 🚀 - Modeller: Grok 4.6 / AI at Meta Muse Spark 1.3 / Claude Fable 5.1 / Google Gemini Gemini 3.8 Flash - Effort: Max & Very high - Agent: Cursor & Opencode Task: Görev, modele tek bir HTML dosyası içinde, dış kaynak kullanmadan, Canvas 2D ile düzlemsel N-cisim kütleçekimi simülasyonu yazdırmak; bu simülasyon açıldığı anda deterministik bir sinematik gösteriyle başlıyor (Kepler yörüngesi → hiyerarşik yıldız sistemi → figure-8 koreografisi → 12 kopyalı kaotik ayrışma → uzun pozlama), ayrıca ~40 saniyelik video kaydı için ayrı bir demo reel modu, gizli fizik self-check'i, korunum diagnostikleri, sürüklenebilir cisimler ve kompakt bir arayüz içeriyor. 🎉 Fiyat/Performans Kazanan: Grok 4.6🎉 🎉 Core Teknik Kazanan: Fable 5.1 🎉 Sebep: Fable, bu benchmark'ın iki tarafını en iyi birlikte çözüyor: solver ve cinematic renderer. Pairwise Newtonian çekirdek, softened potential, conservation diagnostics, Verlet/Yoshida yolu ve validator mimarisi güçlü; runtime self-check sonuçları da dört model içindeki en iyi seviyede. Daha önemlisi, model yalnızca ekrana “PASS” yazmıyor; hidden systems gerçek integrator yoluyla kademeli çalıştırılıyor ve ölçüm sonucundan verdict üretiliyor. Maliyet: - Grok 4.6: $1.10 - Muse Spark 1.3: $1.12 - Gemini 3.8 Flash: $1.3 - Fable 5.1: $6.2 Teknik skor: - Fable 5.1 - 96.4/100 - Grok 4.6 - 92.1/100 - Muse Spark 1.3 - 89.6/100 - Gemini 3.8 Flash - 81.0/100 Performans / $ - Grok 4.6 - 83.7/100 - Muse Spark 1.3 - 80.0/100 - Gemini 3.8 Flash - 62.3/100 - Fable 5.1 - 15.6/100 Teknik İnceleme Metrikleri: 1) Prompt uyumu: Fable'ın substep genişletmesi ve Muse'un bazı spesifikasyonları sadeleştirmesi nedeniyle kimseye 10 vermiyorum. - Fable 5.1: 9.6/10 - Grok 4.6: 9.3/10 - Gemini 3.8 Flash: 8.8/10 - Muse Spark 1.3: 8.2/10 2) Newtonian physics + conservation: Dört modelin de bu kategori şaşırtıcı derecede güçlü. Muse dahil pairwise equal-and-opposite acceleration ve aynı softened potential kernel'ini kullanıyor. - Fable 5.1: 9.9/10 - Grok 4.6: 9.8/10 - Gemini 3.8 Flash: 9.8/10 - Muse Spark 1.3: 9.6/10 3) Symplectic integrasyon + fixed timestep: Gemini'nin Yoshida formülü yanlış değil; puan kaybı scheduler/backlog yönetiminden geliyor. Numerical method doğru, execution model chaos altında sorunlu. - Fable 5.1: 9.6/10 - Grok 4.6: 9.5/10 - Muse Spark 1.3: 9.4/10 - Gemini 3.8 Flash: 8.0/10 4) Self-check / validator doğruluğu: Burada Fable açık lider. Gemini çok yakın; dtExact metodolojik küçük pürüz. Grok/Muse PASS ama validator resolution daha kaba. - Fable 5.1: 10.0/10 - Gemini 3.8 Flash: 9.4/10 - Grok 4.6: 8.6/10 - Muse Spark 1.3: 8.0/10 5) Görsel kalite: Gemini'nin celestial-body shading'i ve UI'sı çok iyi. Fable ise kompozisyon ve “görsel gürültüyü bastırma” açısından biraz daha dengeli. Muse özellikle büyük title choreography ile etkileyici. Grok en restrained olanı. - Fable 5.1: 9.6/10 - Gemini 3.8 Flash: 9.5/10 - Grok 4.6: 9.2/10 - Muse Spark 1.3: 9.1/10 6) Trail rendering: Gemini'nin single-system trail'i güzel; fakat chaos trail timestamp kaynağındaki hata bu kategori için ciddi. - Fable 5.1: 9.7/10 - Grok 4.6: 9.3/10 - Muse Spark 1.3: 9.0/10 - Gemini 3.8 Flash: 7.0/10 Alternatif winner'lar: - En iyi saf numerical correctness: Fable 5.1 - En iyi self-validator: Fable 5.1 - En iyi görsel kalite: Fable 5.1 ≈ Gemini 3.8 Flash - En iyi chaos throughput: Muse Spark 1.3 - En iyi genel mimari: Fable 5.1 - En iyi fiyat/performans: Grok 4.6 - En düşük maliyet: Grok 4.6 - Sadece physics/integrator kodu puanlansaydı: Fable ≈ Grok > Gemini ≈ Muse - Maliyet de kararın temel kriteri olsaydı: Grok > Muse > Gemini >>> Fable

Alican Kiraz

19,607 次观看 • 1 个月前