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。

Been using Claude 3.7 for a couple days and it is very, very good. Its "vibe coding" from language is impressive. I wrote a whole Substack post about the model (& Grok 3), link in reply. Here is a one-shot prompted video game based on the Melville story “Bartleby... show more

Ethan Mollick

358,271 subscribers

155,684 次观看 • 1 年前 •via X (Twitter)

游戏科学技术教育

Anya Rossi• Live Now

Private livecam show

11 条评论

Ethan Mollick 的头像

Ethan Mollick1 年前

Here's the write-up

Page to Pixel Publishing 的头像

Page to Pixel Publishing2 年前

Boost, surf, and weave your way through The Art of Flight, an arcade game about flying multiple ships at the same time. With solo, local co-op, and a leaderboard, there are tons of ways to play. Wishlist on Steam today!

Alex Albert 的头像

Alex Albert1 年前

🙌

Bright Mirror 的头像

Bright Mirror1 年前

Claude 3.7 probably isn't an OOM larger model. Naming it 3.7 seems to imply that, does it not?

Ethan Mollick 的头像

Ethan Mollick1 年前

I dunno its a SoTA model. Anthropic won't tell

arXiv Bangers 的头像

arXiv Bangers1 年前

Banger.

Max the VC 👨‍🚀 的头像

Max the VC 👨‍🚀1 年前

Beautifully concerning

John 的头像

John1 年前

I don’t get why they don’t have search as a capability yet. Basic grounding tech.

Bailiwick 的头像

Bailiwick1 年前

No button to repeatedly say he’d prefer not to?

Ethan Mollick 的头像

Ethan Mollick1 年前

Did you watch the video? That's the mechanic.

Purple Pepe 的头像

Purple Pepe1 年前

oh man emollick you are speaking my jargon now Claude 3.7 vibing with language coding Ribbit

相关视频

Been using the new Claude 3.5 model as a tester and now that it is out, I can say it is very very impressive, and the "artifacts" that it generates are like a simpler version of Code Interpreter This is a real-time video of me creating a playable game and editing it with Claude

Been using the new Claude 3.5 model as a tester and now that it is out, I can say it is very very impressive, and the "artifacts" that it generates are like a simpler version of Code Interpreter This is a real-time video of me creating a playable game and editing it with Claude

Ethan Mollick

162,274 次观看 • 2 年前

Started playtesting our entry for @levelsio vibe coding game jam! We built a Fortnite / CoD deathmatch game with a Minecraft aesthetic using the game engine, which is based on Three.js Game was vibe coded using agentic Claude 3.5/3.7 with context of the HYTOPIA SDK

Started playtesting our entry for @levelsio vibe coding game jam! We built a Fortnite / CoD deathmatch game with a Minecraft aesthetic using the game engine, which is based on Three.js Game was vibe coded using agentic Claude 3.5/3.7 with context of the HYTOPIA SDK

ArkDev | HYTOPIA

565,713 次观看 • 1 年前

Grok is insanely good in coding. I present to you: Grok Theft Auto A game in the stlye of GTA 1 Built on Grok based on a few prompts. The car sounds are from Grok Imagine.

Grok is insanely good in coding. I present to you: Grok Theft Auto A game in the stlye of GTA 1 Built on Grok based on a few prompts. The car sounds are from Grok Imagine.

Testlabor

4,161,269 次观看 • 11 个月前

I've spent the last 2 days vibe coding with Grok and Claude Sonnet I'm making a hybrid battle royale game in HYTOPIA that is a cross of Fortnite + Minecraft. It's feeling really good! Here's a video demoing the features built in 6 hours and an explanation of the game!

I've spent the last 2 days vibe coding with Grok and Claude Sonnet I'm making a hybrid battle royale game in HYTOPIA that is a cross of Fortnite + Minecraft. It's feeling really good! Here's a video demoing the features built in 6 hours and an explanation of the game!

ArkDev | HYTOPIA

12,788 次观看 • 1 年前

It's finally here: Georgetown Georgetown is the world's most intelligent, creative, and fastest model. Georgetown dramatically outperforms Grok 3, Claude 3.7 Sonnet, and GPT 4.5. Reply with "georgetown" for early access.

It's finally here: Georgetown Georgetown is the world's most intelligent, creative, and fastest model. Georgetown dramatically outperforms Grok 3, Claude 3.7 Sonnet, and GPT 4.5. Reply with "georgetown" for early access.

Hayden

19,893 次观看 • 1 年前

It's finally here: Brampton Brampton is the world's most intelligent, creative, and fastest model. Brampton dramatically outperforms Grok 3, Claude 3.7 Sonnet, and GPT 4.5. Reply with "brampton" for early access.

It's finally here: Brampton Brampton is the world's most intelligent, creative, and fastest model. Brampton dramatically outperforms Grok 3, Claude 3.7 Sonnet, and GPT 4.5. Reply with "brampton" for early access.

New

2,056,403 次观看 • 1 年前

A Halloween movie I wrote and produced is free on Tubi or $3 on Amazon/Apple. We shot it in 16 days on an ultra low budget. It was the very first feature script I ever wrote. Learned a lot. Give it a watch if you’re looking for something new (to you)!

A Halloween movie I wrote and produced is free on Tubi or $3 on Amazon/Apple. We shot it in 16 days on an ultra low budget. It was the very first feature script I ever wrote. Learned a lot. Give it a watch if you’re looking for something new (to you)!

ʟᴜᴋᴇ ʙᴀʀɴᴇᴛᴛ 🎄

46,026 次观看 • 9 个月前

Got introduced to , an AI code assistant specialised for Unity by Julian Park and after dabbling with it for a day, I am really impressed with how good it is for vibe coding on the Unity Game Engine. Bezi early impressions: - Bezi works direcly on Unity with a Plugin, this means that I don't need a Unity MCP - Because Bezi is built for Unity, the success rate of feature implementations is visibly higher than general coding models - It was able to integrate Unity store assets like a Weather system to this game pretty seamlessly - I was able to add a fishing database, lighting and weather systems into this game fairly quickly I'm very impressed with the results with Bezi so far. I feel that vibe coding a full indie game on Unity and releasing it on Steam, Mobile and Web is within reach. This also validates one thing that I have been suspecting: A specialised model designed for a specific use case can perform better than a general model at the particular domain. Very exciting!

Got introduced to , an AI code assistant specialised for Unity by Julian Park and after dabbling with it for a day, I am really impressed with how good it is for vibe coding on the Unity Game Engine. Bezi early impressions: - Bezi works direcly on Unity with a Plugin, this means that I don't need a Unity MCP - Because Bezi is built for Unity, the success rate of feature implementations is visibly higher than general coding models - It was able to integrate Unity store assets like a Weather system to this game pretty seamlessly - I was able to add a fishing database, lighting and weather systems into this game fairly quickly I'm very impressed with the results with Bezi so far. I feel that vibe coding a full indie game on Unity and releasing it on Steam, Mobile and Web is within reach. This also validates one thing that I have been suspecting: A specialised model designed for a specific use case can perform better than a general model at the particular domain. Very exciting!

Danny Limanseta

48,991 次观看 • 4 个月前

Finished the failed DmC reboot It's fine. The gameplay is very fine and I very much see the inspirations 5 took from this game However as for the story. Even if I forget this is called Devil May Cry and its something else entirely, its still not a good story. Like holy shit I was cringing like crazy from this story

Finished the failed DmC reboot It's fine. The gameplay is very fine and I very much see the inspirations 5 took from this game However as for the story. Even if I forget this is called Devil May Cry and its something else entirely, its still not a good story. Like holy shit I was cringing like crazy from this story

BlackBlur #ThankYouToriyama

70,436 次观看 • 1 个月前

I beat 34% of Balatro using a Claude Computer-Use Agent Based on my twitter agent (Sky the AI ✨). Here is the youtube video I made about it:

I beat 34% of Balatro using a Claude Computer-Use Agent Based on my twitter agent (Sky the AI ✨). Here is the youtube video I made about it:

Bob

94,398 次观看 • 1 年前

It’s the Monday Morning Pupdate Video In this video you will find: 😫 A little cat who got sick 😢 Very Sick 😠But Fought Back 🥹 And Came Home 😃 It is the very Best Way To Start Your Week For the complete medical breakdown too long to explain in a video please see our Substack where Jason wrote a detailed blog about it. You can find the link in our pinned post.

It’s the Monday Morning Pupdate Video In this video you will find: 😫 A little cat who got sick 😢 Very Sick 😠But Fought Back 🥹 And Came Home 😃 It is the very Best Way To Start Your Week For the complete medical breakdown too long to explain in a video please see our Substack where Jason wrote a detailed blog about it. You can find the link in our pinned post.

Bunsen, Beaker, Bernoulli & Brix

18,676 次观看 • 24 天前

Wow, Sonnet 3.7 w/ Thinking just solved a problem no other model could solve yet. "Can you write the most intricate cloth simulation in p5js" Grok 3 and o1 pro had no usable results. This is truly the best "vibe coding" model.

Wow, Sonnet 3.7 w/ Thinking just solved a problem no other model could solve yet. "Can you write the most intricate cloth simulation in p5js" Grok 3 and o1 pro had no usable results. This is truly the best "vibe coding" model.

Deedy

876,800 次观看 • 1 年前

🇺🇸 X is rolling out a single AI system, “Phoenix” to run the entire feed using Grok. One model deciding what you see based on predicted engagement. Your timeline’s about to feel very different…

🇺🇸 X is rolling out a single AI system, “Phoenix” to run the entire feed using Grok. One model deciding what you see based on predicted engagement. Your timeline’s about to feel very different…

Mario Nawfal

124,271 次观看 • 3 个月前

I built a complex history feature for my Figma to Code plugin in 3 prompts. This is a 30-min tutorial using Claude Code. The difference in code generation between gpt-4o, Claude 3.5 and 3.7 is insane. 3.7 produces near-perfect results and is far more consistent. It's really a designer's best friend, not missing details from the design, like adaptive layout, outlines, spacing, etc. It seems like the new model has great taste now.

I built a complex history feature for my Figma to Code plugin in 3 prompts. This is a 30-min tutorial using Claude Code. The difference in code generation between gpt-4o, Claude 3.5 and 3.7 is insane. 3.7 produces near-perfect results and is far more consistent. It's really a designer's best friend, not missing details from the design, like adaptive layout, outlines, spacing, etc. It seems like the new model has great taste now.

Meng To

32,475 次观看 • 1 年前

I wrote out one of my very NSFW fantasies a couple of days ago and I just recorded the audio version of it. Full version is you know where ;p 🖤

I wrote out one of my very NSFW fantasies a couple of days ago and I just recorded the audio version of it. Full version is you know where ;p 🖤

Listen to Lara

14,977 次观看 • 3 个月前

Claude Code with Sonnet 4.5 is actually incredible I gave it a prompt for a super complex app, and it one shot the entire thing In this video I walk you through how to use Claude Code to build a prompt library app you can start using immediately (no coding experience required):

Claude Code with Sonnet 4.5 is actually incredible I gave it a prompt for a super complex app, and it one shot the entire thing In this video I walk you through how to use Claude Code to build a prompt library app you can start using immediately (no coding experience required):

Alex Finn

40,955 次观看 • 9 个月前

MiniMax M2.1 is officially live🚀 Built for real-world coding and AI-native organizations — from vibe builds to serious workflows. A SOTA 10B-activated OSS coding & agent model, scoring 72.5% on SWE-multilingual and 88.6% on our newly open-sourced VIBE-bench, exceeding leading closed-source models like Gemini 3 Pro and Claude 4.5 Sonnet. The most powerful OSS model for the agentic era is here.

MiniMax M2.1 is officially live🚀 Built for real-world coding and AI-native organizations — from vibe builds to serious workflows. A SOTA 10B-activated OSS coding & agent model, scoring 72.5% on SWE-multilingual and 88.6% on our newly open-sourced VIBE-bench, exceeding leading closed-source models like Gemini 3 Pro and Claude 4.5 Sonnet. The most powerful OSS model for the agentic era is here.

MiniMax (official)

1,073,688 次观看 • 6 个月前

GPT-5 is actually very good at coding. I have to be honest: I didn't like the model when it first came out, but I've grown to appreciate it since then. I feel my hit rate of getting one-shot solutions is now much higher than before. I recorded a quick video about this.

GPT-5 is actually very good at coding. I have to be honest: I didn't like the model when it first came out, but I've grown to appreciate it since then. I feel my hit rate of getting one-shot solutions is now much higher than before. I recorded a quick video about this.

Santiago

32,532 次观看 • 10 个月前