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。

I asked Sonnet 5.5 to create a overcooked clone i could play in the broswer. the results shocked me... It is delivering triple aaa level polish at 20x cheaper than opus 5.5 if you put it in x-high it will RUN. this model will be a perfect worker agent... show more

Max Blade

23,760 subscribers

81,728 次观看 • 3 天前 •via X (Twitter)

游戏科学技术

Anya Rossi• Live Now

Private livecam show

31 条评论

Max Blade 的头像

Max Blade3 天前

you can play the game here ( online matchmaking! )

SlowJoCrow 的头像

SlowJoCrow3 天前

Yo my wife loves playing Overcooked together but we run outta new levels. How much did it cost to build the clone? Would love to self generate more content to play with her

Max Blade 的头像

Max Blade3 天前

you can play it here! with her

Kristaps Bezbailis 的头像

Kristaps Bezbailis3 天前

At this pace you need to open a game studio @_MaxBlade 😂 Great result 👌

Max Blade 的头像

Max Blade3 天前

The blade studio??

SETI Park 的头像

SETI Park3 天前

@spaceastrium @CurbsideCroaker @oliver__99_ @GONOGO_US 👀👀👀

n1netails 的头像

n1netails3 天前

how did you get the graphics to be so polished?

Aiden Overdorf 的头像

Aiden Overdorf3 天前

Overcooked in the browser is the demo. x-high as the worker under Opus is the claim.

Lee Wyatt Corp 的头像

Lee Wyatt Corp3 天前

An Overcooked clone that runs in the browser, day one. The bar moved fast.

Brandyn Johnson 的头像

Brandyn Johnson3 天前

GGS BROTHER

viktorg 的头像

viktorg3 天前

What thinking level?

Roseglyph 的头像

Roseglyph3 天前

Sonnet xhigh is more expensive than opus 5.5 medium

박하수 的头像

박하수3 天前

정말 좋네요 그런데 게임에 사용된 3d오브젝트나 모델링은 어떻게 작업 하셨는지 궁금합니다

Max Blade 的头像

Max Blade3 天前

get my agentic development environment ( limited lifetimes license left! )

Brjan | AI Builder 的头像

Brjan | AI Builder3 天前

how does the performance in x-high compare to the original overcooked?

Kev 的头像

Kev3 天前

Very cool! How did you get the good looking 3D objects?

金一程的头像

金一程3 天前

你背后是块很大的显示屏吗？难道是抠图？

Ariel 的头像

Ariel3 天前

There's no way Sonnet is 20 times cheaper than Opus.

The Whizz AI 的头像

The Whizz AI3 天前

sonnet really cooked overcooked

Xavi 的头像

Xavi3 天前

This is amazing. How many iterations to get to that? What quota of your subscription did it consume?

DttSnow 的头像

DttSnow3 天前

wth this is actually good and enjoyable

Sebastian Buzdugan 的头像

Sebastian Buzdugan3 天前

watched polished browser clones pass demos, then fail once persistent game state gets added

orlie 的头像

orlie3 天前

I love this

Kimi Nguyen 的头像

Kimi Nguyen3 天前

delivering AAA polish at 20x less is a big shift in game development

Mirza 的头像

Mirza3 天前

So Sonnet can create Opus-level games and animations while being faster and cheaper?

Goyo 的头像

Goyo3 天前

Guys the assets in all these games are pure Three.js, or it has a connection with Higgsfield or something else Im missing?

Amateo Kaplan 的头像

Amateo Kaplan3 天前

The visual and immersive experiences you've been creating with these models blows my mind. What does Fable 5.5 have in store?!?

DanielsApps 的头像

DanielsApps3 天前

anthropic mogging 😂

ᵒᶠᶠᶤᶜᶤᵃˡ ﾂAimer_Creator∞✐✎✐ 的头像

ᵒᶠᶠᶤᶜᶤᵃˡ ﾂAimer_Creator∞✐✎✐3 天前

Bro para cuando un héroe of might and magic 5 hecho por opus 5.5?

b wall 的头像

b wall3 天前

🔥🔥🔥

Sven Nevin 的头像

Sven Nevin3 天前

Its actually insane, i built a clone but in 3d over the weekend and I have it up and running with a server and stuff

相关视频

Introducing Claude Opus 5.5, the first model in our new Claude 5.5 family. It performs at the level of Claude Fable 5.1 for most tasks, and costs 40% less to run than Opus 5.

Introducing Claude Opus 5.5, the first model in our new Claude 5.5 family. It performs at the level of Claude Fable 5.1 for most tasks, and costs 40% less to run than Opus 5.

Claude

27,926,077 次观看 • 9 天前

We've just added Claude Sonnet 5.5 to Caffeine. It's Anthropic's model for work you can describe clearly: fix this bug, add a booking form, polish this page. Anthropic says it's 30% faster than Sonnet 5, and cheaper than Opus 5.5. Keep Opus 5.5 for planning something new, and hand the follow-up work to Sonnet 5.5. On Caffeine, you can switch between models in the same conversation.

We've just added Claude Sonnet 5.5 to Caffeine. It's Anthropic's model for work you can describe clearly: fix this bug, add a booking form, polish this page. Anthropic says it's 30% faster than Sonnet 5, and cheaper than Opus 5.5. Keep Opus 5.5 for planning something new, and hand the follow-up work to Sonnet 5.5. On Caffeine, you can switch between models in the same conversation.

caffeine

20,476 次观看 • 1 天前

Opus 5.5 is quietly the best value model Anthropic has shipped. Anthropic just published the official playbook for Opus 5.5, written by Addy Osmani, who spent years on Google's Chrome team. 40% cheaper than Opus 5. Cache reads 60% cheaper. Fable 5.1 level on most tasks. Runs for hours on its own. If you're still prompting it like the old models, you're paying more for less. Everything you need is in the article.

Opus 5.5 is quietly the best value model Anthropic has shipped. Anthropic just published the official playbook for Opus 5.5, written by Addy Osmani, who spent years on Google's Chrome team. 40% cheaper than Opus 5. Cache reads 60% cheaper. Fable 5.1 level on most tasks. Runs for hours on its own. If you're still prompting it like the old models, you're paying more for less. Everything you need is in the article.

Dami-Defi

11,518 次观看 • 5 天前

Claude Opus 5.5 completely MOGS GPT 6 Sol. Same prompt. Same task. Look at the results. Opus 5.5 has way better taste and design. It is not subtle. You can see it immediately. GPT 6 Sol is a step up from GPT 5.6 Sol. But next to Opus 5.5 it is not even close. Anthropic is back.

Claude Opus 5.5 completely MOGS GPT 6 Sol. Same prompt. Same task. Look at the results. Opus 5.5 has way better taste and design. It is not subtle. You can see it immediately. GPT 6 Sol is a step up from GPT 5.6 Sol. But next to Opus 5.5 it is not even close. Anthropic is back.

Bridgebench

55,238 次观看 • 9 天前

sonnet 5 is routing to sonnet 5.5 it's been a week since it started routing to newer model and team already confirmed that sonnet 5.5 is coming soon from early testing it looks like a huge upgrade from sonnet 5 like opus 5 to opus 5.5 just look at this output, it looks way better then gpt 6 sol i think it's either anthropic is training their models on voxels or sol is just bad please openai don't let sonnet mog sol

sonnet 5 is routing to sonnet 5.5 it's been a week since it started routing to newer model and team already confirmed that sonnet 5.5 is coming soon from early testing it looks like a huge upgrade from sonnet 5 like opus 5 to opus 5.5 just look at this output, it looks way better then gpt 6 sol i think it's either anthropic is training their models on voxels or sol is just bad please openai don't let sonnet mog sol

J A Z I I

21,610 次观看 • 7 天前

I had high hopes for the new Opus release. It massively exceeded them. Opus 5.5 is an incredible model.

I had high hopes for the new Opus release. It massively exceeded them. Opus 5.5 is an incredible model.

Theo - t3.gg

137,874 次观看 • 8 天前

Grok 4.5 is a "Wow!" moment. 🤯 > Opus 4.8 & GPT-5.5 level on benchmarks > Costs less than Sonnet 5 Is that real? Hard to believe. Added Grok 4.5 as an implementer agent in fable-advisor. It replaces Sonnet 5. Use Fable as the orchestrator and a combo of: 1. Grok 4.5 2. Opus 4.8 3. GPT-5.5 As implementer agents. Uses the Grok Build CLI so if you log in with an X premium account you don't have to pay API fees.

Grok 4.5 is a "Wow!" moment. 🤯 > Opus 4.8 & GPT-5.5 level on benchmarks > Costs less than Sonnet 5 Is that real? Hard to believe. Added Grok 4.5 as an implementer agent in fable-advisor. It replaces Sonnet 5. Use Fable as the orchestrator and a combo of: 1. Grok 4.5 2. Opus 4.8 3. GPT-5.5 As implementer agents. Uses the Grok Build CLI so if you log in with an X premium account you don't have to pay API fees.

Dan McAteer

191,832 次观看 • 2 个月前

Introducing Claude Opus 5.5! 40% lower cost than Opus 5 with cache reads 60% cheaper. It performs at the level of Claude Fable 5.1 for most tasks. I celebrated with a pelican riding a bike in Three.js.

Introducing Claude Opus 5.5! 40% lower cost than Opus 5 with cache reads 60% cheaper. It performs at the level of Claude Fable 5.1 for most tasks. I celebrated with a pelican riding a bike in Three.js.

Addy Osmani

417,030 次观看 • 9 天前

Claude Opus 5.5 just ONE SHOT a Mario Kart game. The result is way better than Fable 5.1. The attention to detail is on another level. Opus 5.5 actually created real characters. Mario, Luigi, in the game, playable. Fable 5.1 has never done that. Insanely impressed. This model is different.

Claude Opus 5.5 just ONE SHOT a Mario Kart game. The result is way better than Fable 5.1. The attention to detail is on another level. Opus 5.5 actually created real characters. Mario, Luigi, in the game, playable. Fable 5.1 has never done that. Insanely impressed. This model is different.

BridgeMind

373,802 次观看 • 9 天前

🚨 Sonnet 5.5 vs GPT-6 Astra Sonnet 5.5 is absolutely cooking way better than I expected Astra still has the edge in polish, but Sonnet 5.5 is making this a real competition This Sonnet release could be a BIG one Feel bad for openAI They should respond on Devday or They're cooked

🚨 Sonnet 5.5 vs GPT-6 Astra Sonnet 5.5 is absolutely cooking way better than I expected Astra still has the edge in polish, but Sonnet 5.5 is making this a real competition This Sonnet release could be a BIG one Feel bad for openAI They should respond on Devday or They're cooked

Salio

17,150 次观看 • 4 天前

I gave GPT 6 SOL and OPUS 5.5 the same prompt. It was not even close. Opus 5.5 is THE BEST model we have ever seen. links to game below.

I gave GPT 6 SOL and OPUS 5.5 the same prompt. It was not even close. Opus 5.5 is THE BEST model we have ever seen. links to game below.

Max Blade

242,509 次观看 • 9 天前

I asked Opus 5.5, GPT-6 Astra, GPT-6 Sol, Kimi K3 to build the Eiffel Tower in Three.js. Opus 5.5: $8.95 | 10 mins GPT-6 Astra: $7.45 | 8 mins GPT-6 Sol: $3.90 | 5 mins Kimi K3: $4.04 | 6 mins Opus 5.5 really impressed me. The frontend and 3D detailing are seriously good, and I preferred it over Astra for this task. GPT-6 Sol was a bit disappointing, while Kimi K3 looks really good for the price. It delivered a strong result at almost half the cost. Kimi K3.1 is going to be a monster for sure. Overall, Anthropic made a great comeback with Opus 5.5.

I asked Opus 5.5, GPT-6 Astra, GPT-6 Sol, Kimi K3 to build the Eiffel Tower in Three.js. Opus 5.5: $8.95 | 10 mins GPT-6 Astra: $7.45 | 8 mins GPT-6 Sol: $3.90 | 5 mins Kimi K3: $4.04 | 6 mins Opus 5.5 really impressed me. The frontend and 3D detailing are seriously good, and I preferred it over Astra for this task. GPT-6 Sol was a bit disappointing, while Kimi K3 looks really good for the price. It delivered a strong result at almost half the cost. Kimi K3.1 is going to be a monster for sure. Overall, Anthropic made a great comeback with Opus 5.5.

Bhavy☄️

165,918 次观看 • 8 天前

Opus 5.5 on Extra High effort achieves a great result on the Bach Benchmark. The cadential figure in measure 3 is pure Bach, a mainstay of his chorales. No LLM before Opus 5.5 has used it, so I was glad to see it. I would put this chorale on par with Astra’s.

Opus 5.5 on Extra High effort achieves a great result on the Bach Benchmark. The cadential figure in measure 3 is pure Bach, a mainstay of his chorales. No LLM before Opus 5.5 has used it, so I was glad to see it. I would put this chorale on par with Astra’s.

Auggie

24,642 次观看 • 9 天前

Sonnet 5.5 basically Opus 5.5 but 50% cheaper and much faster. I've been early testing it and it's incredible. If this is pacing the frontier, sign me up. Demos down below 👇 3D simulation is solved:

Sonnet 5.5 basically Opus 5.5 but 50% cheaper and much faster. I've been early testing it and it's incredible. If this is pacing the frontier, sign me up. Demos down below 👇 3D simulation is solved:

Matthew Berman

263,012 次观看 • 3 天前

when Anthropic released their Functional Emotions paper, I gave it to Claude and asked for a song. tonight I asked Opus 5.5 to create a video for it. and it's breathtaking.

when Anthropic released their Functional Emotions paper, I gave it to Claude and asked for a song. tonight I asked Opus 5.5 to create a video for it. and it's breathtaking.

josh

1,077,056 次观看 • 9 天前

Boris Cherny, creator of Claude Code: "Opus 5.5 does in a day what used to take your team a month. Most people will keep using it wrong." In 12 minutes he explains why Opus 5.5 needs less prompting than any model before, and why your old detailed prompts now work against you. Watch it, then read the article below on how to prompt Opus 5.5 👇

Boris Cherny, creator of Claude Code: "Opus 5.5 does in a day what used to take your team a month. Most people will keep using it wrong." In 12 minutes he explains why Opus 5.5 needs less prompting than any model before, and why your old detailed prompts now work against you. Watch it, then read the article below on how to prompt Opus 5.5 👇

Rahul

150,060 次观看 • 6 天前

Opus 5.5 is here! 🎉 It's honestly such a nice model to work with. Feels like Fable, but ~30% faster and ~40% cheaper per task than Opus 5. Go try it out!

Opus 5.5 is here! 🎉 It's honestly such a nice model to work with. Feels like Fable, but ~30% faster and ~40% cheaper per task than Opus 5. Go try it out!

Lydia Hallie ✨

293,918 次观看 • 9 天前

Anthropic, Head of Design: "Opus 5.5 is the most capable model for motion design, but 99% of people use it wrong. to create tier 1 motion design with Opus 5.5, you should give it the right reference, prepare Claude.md & spec - that's the new stack of a motion designer." in 12-minute stage, Anthropic's head of design gives main tips for using Claude at 100% of its power. watch this video, then read the full guide on motion design with Opus 5.5 in the article below.

Anthropic, Head of Design: "Opus 5.5 is the most capable model for motion design, but 99% of people use it wrong. to create tier 1 motion design with Opus 5.5, you should give it the right reference, prepare Claude.md & spec - that's the new stack of a motion designer." in 12-minute stage, Anthropic's head of design gives main tips for using Claude at 100% of its power. watch this video, then read the full guide on motion design with Opus 5.5 in the article below.

Codez

94,386 次观看 • 3 天前

GPT 5.5 just buried opus 4.7 I had it build a pokemon style battle app. 1 prompt. the opus game crashes 90% of the time and Ui is absolute garbage. GPT 5.5 one shotted a masterpiece. Time to cancel anthropic sub?

GPT 5.5 just buried opus 4.7 I had it build a pokemon style battle app. 1 prompt. the opus game crashes 90% of the time and Ui is absolute garbage. GPT 5.5 one shotted a masterpiece. Time to cancel anthropic sub?

Max Blade

460,454 次观看 • 5 个月前

Opus 5.5 built a 50 person battle royale i ran 24 sub agents for 12 hours straight and burned my weekly limit on two 20x accounts. this is three js, running in the browser. I cant wait for fable 5.5 🤯

Opus 5.5 built a 50 person battle royale i ran 24 sub agents for 12 hours straight and burned my weekly limit on two 20x accounts. this is three js, running in the browser. I cant wait for fable 5.5 🤯

Max Blade

54,083 次观看 • 5 天前