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。

Some good progress on vibe coding this Street Fighter-like game. > Cursor with Opus 4.8 for majority of code > Spriterrific w/ Grok Imagine for animations Was a good learning experience compared to making a platformer Probably worth a full tutorial?

Chong-U

12,828 subscribers

10,318 次观看 • 2 个月前 •via X (Twitter)

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

I gave the Unity CLI a try - and it's GOOD! Connected with Grok 4.5 via Grok Build - it handled the Editor by itself. Took the 2d platformer template and told Grok to give it a visual uplift, while keeping the game mechanics. Spriterrific for the character animations and Nano Banana 2 lite for the static sprites. I think this is a huge unlock for gamedevs, especially those who want to use Unity!

I gave the Unity CLI a try - and it's GOOD! Connected with Grok 4.5 via Grok Build - it handled the Editor by itself. Took the 2d platformer template and told Grok to give it a visual uplift, while keeping the game mechanics. Spriterrific for the character animations and Nano Banana 2 lite for the static sprites. I think this is a huge unlock for gamedevs, especially those who want to use Unity!

Chong-U

41,658 次观看 • 15 天前

Just a couple of prompts from start to finish into a playable game! Pixel-perfect art > Codex App w/ GPT 5.5 High > Images 2.0 for animations (except walkcycles) > WAN 2.0 for walkcycles (cheap!) > 11Labs for bgm/sfx (in 1 prompt) > Phaser 4 Sound ON🔉 Full tutorial anyone?

Just a couple of prompts from start to finish into a playable game! Pixel-perfect art > Codex App w/ GPT 5.5 High > Images 2.0 for animations (except walkcycles) > WAN 2.0 for walkcycles (cheap!) > 11Labs for bgm/sfx (in 1 prompt) > Phaser 4 Sound ON🔉 Full tutorial anyone?

Chong-U

55,906 次观看 • 3 个月前

A card for that special someone who also happens to like Street Fighter. I edited a back sprite of Zangief to get a good overlay. "I Love Spinning Time With You"

A card for that special someone who also happens to like Street Fighter. I edited a back sprite of Zangief to get a good overlay. "I Love Spinning Time With You"

Goh_Billy

452,091 次观看 • 2 年前

I'm making good progress on porting my 3D Platformer Starter Kit to Babylon.js! I've figured out collisions, gamepad support, some juice, sounds and more. Still need a couple of days to implement the rest of the functions!

I'm making good progress on porting my 3D Platformer Starter Kit to Babylon.js! I've figured out collisions, gamepad support, some juice, sounds and more. Still need a couple of days to implement the rest of the functions!

Kenney

14,789 次观看 • 5 个月前

underrated technique: vibe code a full-custom debug view for code you're writing by hand! in this case, visualizing a parsing algorithm 😎 a clear interactive visualization helps you really grok what's going on step by step, and of course helps with fixing bugs too

underrated technique: vibe code a full-custom debug view for code you're writing by hand! in this case, visualizing a parsing algorithm 😎 a clear interactive visualization helps you really grok what's going on step by step, and of course helps with fixing bugs too

Geoffrey Litt

79,555 次观看 • 1 年前

BREAKING: Anthropic just dropped Opus 4.8—and it is a MONSTER We've been testing for about a week Every 📧 and our verdict is they could've just called it Opus 5, it's that good. Here's our vibe check: - Beats GPT-5.5 on Senior Engineer bench. On our toughest benchmark Opus 4.8 scores a 63—a hair higher than GPT-5.5's score of 62, and a full 30 points higher than Opus 4.7. It tackled a ground-up rewrite of a production codebase, and actually built something that works. HOWEVER: Coding performance varied a lot at different reasoning levels. We recommend using it on xhigh for best results. - Incredibly good writer. Opus 4.8 scored a 79.6 on our writing benchmark—measuring models on real-world writing tasks we do all of the time like essay writing, promo email writing, and more. It beats GPT-5.5 by 6 points. It produces well-written prose with fewer "AI-isms". It's also very good at writing in your voice given the right context. HOWEVER: Writing performance also varied with reasoning levels. Medium reasoning had higher incidence of AI-isms—we found best results with high. - Beast at knowledge work. Opus 4.8 is very good at general knowledge work tasks like report creation, research and more. It produced the best PowerPoint one-shot we've ever seen on our deck generation benchmark. - Emotionally intelligent, willing to question the frame. I've also found it to be quite good at talking through psychological or interpersonal issues. It has a high EQ, and it's also good at not glazing and helping to expand your perspective. Its thought process feels extremely rich and dynamic. THE BAD: These days a model is only as good as its harness, and Codex is still a far superior harness to the Claude Desktop app. This has kept me using Codex + GPT-5.5 as my daily driver, but I am flipping back and forth a lot more between Codex and Claude. Anthropic is back baby! Read the rest on Every 📧:

BREAKING: Anthropic just dropped Opus 4.8—and it is a MONSTER We've been testing for about a week Every 📧 and our verdict is they could've just called it Opus 5, it's that good. Here's our vibe check: - Beats GPT-5.5 on Senior Engineer bench. On our toughest benchmark Opus 4.8 scores a 63—a hair higher than GPT-5.5's score of 62, and a full 30 points higher than Opus 4.7. It tackled a ground-up rewrite of a production codebase, and actually built something that works. HOWEVER: Coding performance varied a lot at different reasoning levels. We recommend using it on xhigh for best results. - Incredibly good writer. Opus 4.8 scored a 79.6 on our writing benchmark—measuring models on real-world writing tasks we do all of the time like essay writing, promo email writing, and more. It beats GPT-5.5 by 6 points. It produces well-written prose with fewer "AI-isms". It's also very good at writing in your voice given the right context. HOWEVER: Writing performance also varied with reasoning levels. Medium reasoning had higher incidence of AI-isms—we found best results with high. - Beast at knowledge work. Opus 4.8 is very good at general knowledge work tasks like report creation, research and more. It produced the best PowerPoint one-shot we've ever seen on our deck generation benchmark. - Emotionally intelligent, willing to question the frame. I've also found it to be quite good at talking through psychological or interpersonal issues. It has a high EQ, and it's also good at not glazing and helping to expand your perspective. Its thought process feels extremely rich and dynamic. THE BAD: These days a model is only as good as its harness, and Codex is still a far superior harness to the Claude Desktop app. This has kept me using Codex + GPT-5.5 as my daily driver, but I am flipping back and forth a lot more between Codex and Claude. Anthropic is back baby! Read the rest on Every 📧:

Dan Shipper 📧

354,163 次观看 • 2 个月前

To show you how beast of a model is opus 5 this sol 5.6 against it that wall where opus is shoooting great wall of china < kimi k3 , qwen 3.8 > we are so back , wait for mac os code to compare with kimi k3

To show you how beast of a model is opus 5 this sol 5.6 against it that wall where opus is shoooting great wall of china < kimi k3 , qwen 3.8 > we are so back , wait for mac os code to compare with kimi k3

Chetaslua

89,662 次观看 • 14 天前

A lot of people have been asking about getting vibe coded games onto mobile phones. Been experimenting with different ways to get stuff running on iOS. Here's a quick Super Crate Box inspired prototype running on the simulator. Hoping to establish a good workflow that would make this easy to do with Claude Code / Codex / Cursor.

A lot of people have been asking about getting vibe coded games onto mobile phones. Been experimenting with different ways to get stuff running on iOS. Here's a quick Super Crate Box inspired prototype running on the simulator. Hoping to establish a good workflow that would make this easy to do with Claude Code / Codex / Cursor.

Chong-U

10,679 次观看 • 6 个月前

And it's live, the frontend still throttle to 250ms updates for now, just monitoring things. Will push the full speed later on after a few performance improvements in the code computing the full order books from Hyperliquid logs files. Was a good day of coding 🦈

And it's live, the frontend still throttle to 250ms updates for now, just monitoring things. Will push the full speed later on after a few performance improvements in the code computing the full order books from Hyperliquid logs files. Was a good day of coding 🦈

𝗶𝗮𝗺𝟰𝘅

10,285 次观看 • 2 个月前

Tesla is worth ~$600B today, but with Robotaxis, it could be worth >$5-7T. Many don’t believe it, but the ones that use, understand, & see the progress of FSD, there’s a good chance it’s going to happen. $TSLA

Tesla is worth ~$600B today, but with Robotaxis, it could be worth >$5-7T. Many don’t believe it, but the ones that use, understand, & see the progress of FSD, there’s a good chance it’s going to happen. $TSLA

Teslaconomics

14,336 次观看 • 2 年前

THIS GUY IS RUNNING CLAUDE CODE ON A NINTENDO 3DS imagine vibe coding a startup from a handheld console that came out in 2011 he built a native SSH terminal for it from scratch in C. GPU-rendered, custom VT100 parser with full truecolor. even added a Nerd Font bitmap atlas so it looks exactly like his desktop terminal the 3DS connects to his Mac over SSH and runs Claude Code straight from it you can now play pokemon while you vibe code all on the same system

THIS GUY IS RUNNING CLAUDE CODE ON A NINTENDO 3DS imagine vibe coding a startup from a handheld console that came out in 2011 he built a native SSH terminal for it from scratch in C. GPU-rendered, custom VT100 parser with full truecolor. even added a Nerd Font bitmap atlas so it looks exactly like his desktop terminal the 3DS connects to his Mac over SSH and runs Claude Code straight from it you can now play pokemon while you vibe code all on the same system

Om Patel

77,692 次观看 • 3 个月前

This is not Grok-4. It's an Opensource AI Coding model soon to be coming out of China. And it works incredibly well with Cline and Claude Code. It's going to be a huge day for AI coding models.

This is not Grok-4. It's an Opensource AI Coding model soon to be coming out of China. And it works incredibly well with Cline and Claude Code. It's going to be a huge day for AI coding models.

Shubham Saboo

220,584 次观看 • 1 年前

there’s ~40% chance that xAI acquires Cursor. or at least some sort of collaborative relation between them. Cursor has the goldmine. mountains of real world dev data, prompts, and codebase patterns from millions of AI-assisted coding sessions. xAI has Colossus. the largest GPU cluster on the planet. imagine the data + insane compute together, that’s disruption of peace for the three largest players. elon is a visionary. he sees it. Grok Code soon!

there’s ~40% chance that xAI acquires Cursor. or at least some sort of collaborative relation between them. Cursor has the goldmine. mountains of real world dev data, prompts, and codebase patterns from millions of AI-assisted coding sessions. xAI has Colossus. the largest GPU cluster on the planet. imagine the data + insane compute together, that’s disruption of peace for the three largest players. elon is a visionary. he sees it. Grok Code soon!

sui ☄️

39,163 次观看 • 3 个月前

"Don't bring a gun to a giant robot fight." - Brain Drain probably. Here's some early Work In Progress sketched animations of one of Brain Drain's attacks for when he arrives in Skullgirls Mobile later this year! #Skullgirls #SkullgirlsBrainDrain

"Don't bring a gun to a giant robot fight." - Brain Drain probably. Here's some early Work In Progress sketched animations of one of Brain Drain's attacks for when he arrives in Skullgirls Mobile later this year! #Skullgirls #SkullgirlsBrainDrain

Skullgirls

156,098 次观看 • 2 年前

She’s. Just. A. Touchy. Person. Probably a good habit for her to break given how many eyes are on her right now But some women are just naturally like this and it has nothing to do with being flirty

She’s. Just. A. Touchy. Person. Probably a good habit for her to break given how many eyes are on her right now But some women are just naturally like this and it has nothing to do with being flirty

Allie ✞

1,961,735 次观看 • 9 个月前

Making of a concept I was working on for a project, I think I’ll be able to develop a good idea here. #UEFN #Fortnite

Making of a concept I was working on for a project, I think I’ll be able to develop a good idea here. #UEFN #Fortnite

Droust

46,981 次观看 • 1 年前

Good for Anthony Volpe. He probably shouldn't be playing much shortstop for the Yankees, and his opportunities will be sparse compared to the last few years, but this was such a huge hit. Especially with the Rays getting walked off in Baltimore.

Good for Anthony Volpe. He probably shouldn't be playing much shortstop for the Yankees, and his opportunities will be sparse compared to the last few years, but this was such a huge hit. Especially with the Rays getting walked off in Baltimore.

Joe Randazzo

59,500 次观看 • 2 个月前

SpaceXai just made grok 4.5 FREE in your coding agent starting today it's xAI's new coding model. 500k context. built for long agent sessions. no card. what you get for $0: -83.3% on terminal-bench 2.1 -64.7% on swe-bench pro - 4.2x more efficient than Opus 4.8 -500k context for big repos -$2/M in, $6/M out once it goes paid what this replaces: -Claude Opus 4.8: $15/M in, $75/M out -SuperGrok: $30-50/mo all for $0 how to set it up (2 min): >curl -fsSL | bash > grok → localhost:8000/v1 > point hermes / aider / opencode / cline to it > model: grok-4.5 Or API key at - base url Works in Hermes, Aider, OpenCode, Cline, Claude Code, and any OpenAI-compatible tool. Important: Free for a limited time. EU waits till mid-July. Rate limits apply. bookmark this before the free window closes

SpaceXai just made grok 4.5 FREE in your coding agent starting today it's xAI's new coding model. 500k context. built for long agent sessions. no card. what you get for $0: -83.3% on terminal-bench 2.1 -64.7% on swe-bench pro - 4.2x more efficient than Opus 4.8 -500k context for big repos -$2/M in, $6/M out once it goes paid what this replaces: -Claude Opus 4.8: $15/M in, $75/M out -SuperGrok: $30-50/mo all for $0 how to set it up (2 min): >curl -fsSL | bash > grok → localhost:8000/v1 > point hermes / aider / opencode / cline to it > model: grok-4.5 Or API key at - base url Works in Hermes, Aider, OpenCode, Cline, Claude Code, and any OpenAI-compatible tool. Important: Free for a limited time. EU waits till mid-July. Rate limits apply. bookmark this before the free window closes

painn

151,174 次观看 • 29 天前