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。

GPT-5.3 Codex is actually pretty insane with Three.js This Minecraft clone works smoothly and it didn't take too long to make I also tried Opus 4.6, but for some reason it got stuck

Angel 🌼

11,700 subscribers

1,127,915 次观看 • 7 个月前 •via X (Twitter)

游戏科学技术

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

Wait… I’m actually obsessed with Codex + GPT-5.4 🤯 Built a Club Penguin clone in 6 prompts. Then used to make it multiplayer. Didn’t expect this but… OpenAI might've officially converted me to Codex for vibe-coding.

Wait… I’m actually obsessed with Codex + GPT-5.4 🤯 Built a Club Penguin clone in 6 prompts. Then used to make it multiplayer. Didn’t expect this but… OpenAI might've officially converted me to Codex for vibe-coding.

Safinaz Elhadary

51,145 次观看 • 6 个月前

I tried Opus 4.6 Max in Cursor with a much more detailed prompt and the results are incredible Functional inventory, health, tools, recipes, and more The only downside is how expensive the model is and it also had to fix some bugs, but it's a pretty strong model overall

I tried Opus 4.6 Max in Cursor with a much more detailed prompt and the results are incredible Functional inventory, health, tools, recipes, and more The only downside is how expensive the model is and it also had to fix some bugs, but it's a pretty strong model overall

Angel 🌼

70,710 次观看 • 7 个月前

I told Claude 4.6 Opus to make a pokemon clone - max effort It reasoned for 1 hour and 30 minutes and used 110k tokens and 2 shotted this absolute behemoth. This is one of the coolest things I’ve ever made with AI

I told Claude 4.6 Opus to make a pokemon clone - max effort It reasoned for 1 hour and 30 minutes and used 110k tokens and 2 shotted this absolute behemoth. This is one of the coolest things I’ve ever made with AI

Chris

659,082 次观看 • 7 个月前

Clawdbot creator Peter Steinberger 🦞 says Claude Opus is his favorite model, but OpenAI Codex is the best for coding: "OpenAI is very reliable. For coding, I prefer Codex because it can navigate large codebases. You can prompt and have 95% certainty that it actually works. With Claude Code you need more tricks to get the same." "But character wise, [Opus] behaves so good in a Discord it kind of feels like a human. I've only really experienced that with Opus."

Clawdbot creator Peter Steinberger 🦞 says Claude Opus is his favorite model, but OpenAI Codex is the best for coding: "OpenAI is very reliable. For coding, I prefer Codex because it can navigate large codebases. You can prompt and have 95% certainty that it actually works. With Claude Code you need more tricks to get the same." "But character wise, [Opus] behaves so good in a Discord it kind of feels like a human. I've only really experienced that with Opus."

TBPN

443,150 次观看 • 8 个月前

Honestly Opus 5.5 is baby AGI. It filmed this launch trailer inside the actual game . I am speechless. This entire Minecraft clone was made with code. Every texture and sound too. Would love for you all to try it and let me know what you think. 👇

Honestly Opus 5.5 is baby AGI. It filmed this launch trailer inside the actual game . I am speechless. This entire Minecraft clone was made with code. Every texture and sound too. Would love for you all to try it and let me know what you think. 👇

AshutoshShrivastava

125,220 次观看 • 4 天前

this is fun!! for comparison I asked Fable to make it with three.js and transformers.js and onnx Depth Anything, but it's not near TypeGPU performance. I've got to learn it now demo: code:

this is fun!! for comparison I asked Fable to make it with three.js and transformers.js and onnx Depth Anything, but it's not near TypeGPU performance. I've got to learn it now demo: code:

Radamés Ajna

34,024 次观看 • 1 个月前

opus 5.5 is a beast model it just made the best minecraft clone i’ve seen yet, even astra couldn’t make anything like this it has water physics, realistic mechanics and pretty much everything but it’s super slow, even slower than astra play here:

opus 5.5 is a beast model it just made the best minecraft clone i’ve seen yet, even astra couldn’t make anything like this it has water physics, realistic mechanics and pretty much everything but it’s super slow, even slower than astra play here:

J A Z I I

75,668 次观看 • 8 天前

I tried Opus 4.7 (xhigh) with my Minecraft prompt It's a very ambitious and creative model, but it feels unreliable It even added mobs and ore generation, but most things were broken and it couldn't fix some

I tried Opus 4.7 (xhigh) with my Minecraft prompt It's a very ambitious and creative model, but it feels unreliable It even added mobs and ore generation, but most things were broken and it couldn't fix some

Angel 🌼

68,508 次观看 • 5 个月前

I have been using GPT-5.3-Codex-Spark all day every day for 2 weeks now. It's incredibly fast (Cerebras) I had a few moments where I felt I could see the future. So far I've tried it in: - Zed - Openclaw - Codex app - Codex cli / pi This is a clue to where we're heading.

I have been using GPT-5.3-Codex-Spark all day every day for 2 weeks now. It's incredibly fast (Cerebras) I had a few moments where I felt I could see the future. So far I've tried it in: - Zed - Openclaw - Codex app - Codex cli / pi This is a clue to where we're heading.

0xSero

22,212 次观看 • 7 个月前

🤯This is crazy... Qwen 3.8 Flash Next IS really good... it basically one shot this, then I just told it to add the MLX-Serve / Qwen structure after. (mixed 4-8bit version) (~90gb ram, it did use full 256k ctx) Prompt: build me a minecraft clone using threejs, npm, typescript, test files, linting, and better graphics than minecraft, make it look good. Just simple block building with the basic minecraft blocks, but make it look really good with amazing graphics. Generated textures and sounds. Benchmaxxing ? Maybe, needs more testing, but I have been seeing some good results on Youtube also.

🤯This is crazy... Qwen 3.8 Flash Next IS really good... it basically one shot this, then I just told it to add the MLX-Serve / Qwen structure after. (mixed 4-8bit version) (~90gb ram, it did use full 256k ctx) Prompt: build me a minecraft clone using threejs, npm, typescript, test files, linting, and better graphics than minecraft, make it look good. Just simple block building with the basic minecraft blocks, but make it look really good with amazing graphics. Generated textures and sounds. Benchmaxxing ? Maybe, needs more testing, but I have been seeing some good results on Youtube also.

David Dalcu

26,075 次观看 • 1 个月前

Opus 5 (before) vs Opus 5 (now) I tested this rocket scene again after people started saying Opus 5 might be getting routed to Opus 5.2. And yeah, the difference is pretty clear. I know these models aren't deterministic, but I ran the same scene multiple times with Opus 5 before, and it never got this level of realism in one shot. If this is actually Opus 5.2, it could be a game-changing model for Anthropic. I’m starting to think Opus 5.2 could mog Astra in frontend and 3D.

Opus 5 (before) vs Opus 5 (now) I tested this rocket scene again after people started saying Opus 5 might be getting routed to Opus 5.2. And yeah, the difference is pretty clear. I know these models aren't deterministic, but I ran the same scene multiple times with Opus 5 before, and it never got this level of realism in one shot. If this is actually Opus 5.2, it could be a game-changing model for Anthropic. I’m starting to think Opus 5.2 could mog Astra in frontend and 3D.

Bhavy☄️

65,527 次观看 • 16 天前

Clone a functional Billion $$ SAAS Part 2 - Figma. Now that Claude Opus 4.6 and Codex 5.3 are available, I decided to try this again. The result - CanvasKit Tools used - Windsurf (retired) Cascade & OpenAI Codex CLI First agent run - 30 minutes Total time spent w/ extra prompting - 3 hours I think this could be a new metric for model evaluations - TTBS (time to billion $$ SAAS 😂) Code and details below:

Clone a functional Billion $$ SAAS Part 2 - Figma. Now that Claude Opus 4.6 and Codex 5.3 are available, I decided to try this again. The result - CanvasKit Tools used - Windsurf (retired) Cascade & OpenAI Codex CLI First agent run - 30 minutes Total time spent w/ extra prompting - 3 hours I think this could be a new metric for model evaluations - TTBS (time to billion $$ SAAS 😂) Code and details below:

nader dabit

30,271 次观看 • 7 个月前

GPT-6.1 Sol isn’t that good I asked it to build the Eiffel Tower in Three.js, and this is what it came up with. It performs pretty well on some other tests, but it failed badly on this scene compared to other models. For me, it still feels below Astra and even Kimi in frontend and 3D. OpenAI says it’s more efficient, but it seems to consume a lot of tokens.

GPT-6.1 Sol isn’t that good I asked it to build the Eiffel Tower in Three.js, and this is what it came up with. It performs pretty well on some other tests, but it failed badly on this scene compared to other models. For me, it still feels below Astra and even Kimi in frontend and 3D. OpenAI says it’s more efficient, but it seems to consume a lot of tokens.

Bhavy☄️

37,861 次观看 • 1 天前

I ADDED MULTIPLAYER AND IT ACTUALLY WORKS :DD Absolutely insane, just 8 hours in starting from scratch Cursor did this, I just asked it!! Marc Köhlbrugge recommended WebRTC so I asked "can you make it multiplayer with webrtc" It used PeerJS, I tried first to do a big room of everybody but THAT didn't work, but it does work 1-on-1 if you share your ID and you can fly with each other 🥹

I ADDED MULTIPLAYER AND IT ACTUALLY WORKS :DD Absolutely insane, just 8 hours in starting from scratch Cursor did this, I just asked it!! Marc Köhlbrugge recommended WebRTC so I asked "can you make it multiplayer with webrtc" It used PeerJS, I tried first to do a big room of everybody but THAT didn't work, but it does work 1-on-1 if you share your ID and you can fly with each other 🥹

@levelsio

1,035,439 次观看 • 1 年前

Opus 4.6 vs Gemini 3 Pro (3/9) prompt: Build a premium interactive isometric 3D cozy room using Vite + React + Three.js (react-three-fiber/drei), with all objects modeled in code (no external assets) and subtle ambient animations. Gemini looks good on initial impression but I feel like I have way more to work with opus here (opus also did light/dark mode and took a quarter of the time to make it).

Opus 4.6 vs Gemini 3 Pro (3/9) prompt: Build a premium interactive isometric 3D cozy room using Vite + React + Three.js (react-three-fiber/drei), with all objects modeled in code (no external assets) and subtle ambient animations. Gemini looks good on initial impression but I feel like I have way more to work with opus here (opus also did light/dark mode and took a quarter of the time to make it).

Dev Ed

77,206 次观看 • 7 个月前

GPT5.4 is an incredible model. I've been playing with it for the last week. This is OpenAI's answer to Anthropic's Opus 4.6. But there's more to it than it seems... Full breakdown:

GPT5.4 is an incredible model. I've been playing with it for the last week. This is OpenAI's answer to Anthropic's Opus 4.6. But there's more to it than it seems... Full breakdown:

Matthew Berman

59,274 次观看 • 6 个月前

this was one of the biggest weeks in AI because claude opus 4.6 and gpt-5.3 codex dropped basically at the SAME time. they solve the same problem in VERY different ways. - opus spins up agent teams and disappears for a while. - codex stays with you and ships ridiculously fast. i tested them both for you in this episode of The Startup Ideas Podcast (SIP) 🧃 (on yt/spot/apple/X) with my pal Morgan we set them up live, tuned them properly, and had each one build a polymarket clone from scratch. you’ll see where each one shines, where it struggles, and which approach actually fits how you work. if you’re trying to decide what to use next, this episode will save you a lot of trial and error.

this was one of the biggest weeks in AI because claude opus 4.6 and gpt-5.3 codex dropped basically at the SAME time. they solve the same problem in VERY different ways. - opus spins up agent teams and disappears for a while. - codex stays with you and ships ridiculously fast. i tested them both for you in this episode of The Startup Ideas Podcast (SIP) 🧃 (on yt/spot/apple/X) with my pal Morgan we set them up live, tuned them properly, and had each one build a polymarket clone from scratch. you’ll see where each one shines, where it struggles, and which approach actually fits how you work. if you’re trying to decide what to use next, this episode will save you a lot of trial and error.

GREG ISENBERG

92,318 次观看 • 7 个月前

$I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)$

I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)

Ian Nuttall

195,173 次观看 • 1 年前

FREE Claude Opus 4.8. FREE GPT 5.5. All free. 7,200 credits. I tested it myself - works. The platform is Gumloop(.)com. Chat interface plus connections into different services. Company raised $50M Here's the exact setup: → Register via Google OAuth or Microsoft OAuth → During onboarding, answer the questions and select every option you can → When asked to connect services, pick Apify, Semrush, and Reducto - no login needed for any of them → Skip the Slack connection → Done correctly, you land 7,200 credits minimum Models inside: Opus 4.6 through 4.8, GPT 5.3 Codex, GPT 5.4, GPT 5.5, Gemini 3 Flash, Gemini 3.1 Pro, Gemini 3.5 Flash, DeepSeek V4 Flash and Pro, Kimi K2.6. No card needed anywhere in this flow. I ran through it myself - fully working. Bookmark this before it gets patched.

FREE Claude Opus 4.8. FREE GPT 5.5. All free. 7,200 credits. I tested it myself - works. The platform is Gumloop(.)com. Chat interface plus connections into different services. Company raised $50M Here's the exact setup: → Register via Google OAuth or Microsoft OAuth → During onboarding, answer the questions and select every option you can → When asked to connect services, pick Apify, Semrush, and Reducto - no login needed for any of them → Skip the Slack connection → Done correctly, you land 7,200 credits minimum Models inside: Opus 4.6 through 4.8, GPT 5.3 Codex, GPT 5.4, GPT 5.5, Gemini 3 Flash, Gemini 3.1 Pro, Gemini 3.5 Flash, DeepSeek V4 Flash and Pro, Kimi K2.6. No card needed anywhere in this flow. I ran through it myself - fully working. Bookmark this before it gets patched.

Atenov int.

24,443 次观看 • 3 个月前

OPUS 4.6 WAS NERFED DUE TO DEMAND BUT OPUS 4.5 DOES NOT SEEM TO BE HIT this guy ran the same test on both models. Opus 4.6 fails consistently but Opus 4.5 passes every time he switched back to Opus 4.5 on Claude Code and said "what a difference, feels like i got Opus back finally" he is now using this test as a "quantization canary" that runs it at the start of every session before doing real work. if it fails, the model is degraded. five Opus 4.6 windows in a row failed the untransparent nerfing is pushing people to cancel their Max plans if you've been feeling like Opus got dumber lately, you're not imagining it i'd suggest switching to Opus 4.5 to see the difference for yourself

OPUS 4.6 WAS NERFED DUE TO DEMAND BUT OPUS 4.5 DOES NOT SEEM TO BE HIT this guy ran the same test on both models. Opus 4.6 fails consistently but Opus 4.5 passes every time he switched back to Opus 4.5 on Claude Code and said "what a difference, feels like i got Opus back finally" he is now using this test as a "quantization canary" that runs it at the start of every session before doing real work. if it fails, the model is degraded. five Opus 4.6 windows in a row failed the untransparent nerfing is pushing people to cancel their Max plans if you've been feeling like Opus got dumber lately, you're not imagining it i'd suggest switching to Opus 4.5 to see the difference for yourself

Om Patel

696,175 次观看 • 5 个月前