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。

wait actually Claude Code mods are sick. I vibe-coded my own spinner that watches what the main agent is doing and uses Sonnet 5.5 to turn it into little cartoons in real time

Anshu

16,695 subscribers

175,888 次观看 • 1 天前 •via X (Twitter)

游戏科学技术

Anya Rossi• Live Now

Private livecam show

15 条评论

Thariq 的头像

Thariq1 天前

@pdrmnvd This is sick

lucas 的头像

lucas1 天前

haiku 5.5 would make instant ui reality

Anshu 的头像

Anshu1 天前

I know, that would be amazing! But Sonnet is pretty fast and cheap

lucas 的头像

lucas1 天前

true

Boris Cherny 的头像

Boris Cherny1 天前

Super cool 🔥

air 的头像

air1 天前

Wow! Tutorial please? 🙏

Anshu 的头像

Anshu1 天前

The way Claude did this was really interesting. It’s late here but will post more details tomorrow. The mod API doesn’t allow code execution, so we had to build a small custom language and interpreter for Sonnet

Apo's T w itter 的头像

Apo's T w itter1 天前

this is so cool

enji vi 的头像

enji vi1 天前

Ayo this is so sool

valent 的头像

valent1 天前

Hey, buddies! My friends and I made this. Right in the notch

Nicholas Dunzelman 的头像

Nicholas Dunzelman1 天前

dm'd you!

noel 的头像

noel1 天前

Watching the tool-call stream with a second model is a nice use of mods. Since the watcher sees every step anyway, flagging when the main agent repeats itself seems like a cheap next step.

Deon Holo 的头像

Deon Holo1 天前

Lol the bug looks like a moving, gaping butthole.

Andre Buckingham 🧙‍♂️ 的头像

Andre Buckingham 🧙‍♂️1 天前

more exposed surfaces like this has really been missing in ClaudeCode... it's what makes hermes so good, so they will win on this...

Jeff Bruchado 的头像

Jeff Bruchado1 天前

please give failed tool calls the little cartoon fall sound

相关视频

Had Claude Code build a little plugin that visualizes the work Claude Code is doing as agents working in an office, with agents doing work and passing information to each other. New subagents are hired, they acquire skills, and they turn in completed work. Fun start.

Had Claude Code build a little plugin that visualizes the work Claude Code is doing as agents working in an office, with agents doing work and passing information to each other. New subagents are hired, they acquire skills, and they turn in completed work. Fun start.

Ethan Mollick

468,672 次观看 • 8 个月前

Claude Sonnet 4.8 is imminent. Most likely dropping today. Sonnet 4.6 is starting to look outdated. Look at the Flappy Bird test on BridgeBench. GPT 5.5 and Claude Opus 4.7 have moved past it. The model that used to be the default for most vibe coders is falling behind. Anthropic needs Sonnet 4.8 to close the gap. The second it drops, we're running it through every BridgeBench test and posting the results live. New Sonnet day. Let's see what Anthropic has.

Claude Sonnet 4.8 is imminent. Most likely dropping today. Sonnet 4.6 is starting to look outdated. Look at the Flappy Bird test on BridgeBench. GPT 5.5 and Claude Opus 4.7 have moved past it. The model that used to be the default for most vibe coders is falling behind. Anthropic needs Sonnet 4.8 to close the gap. The second it drops, we're running it through every BridgeBench test and posting the results live. New Sonnet day. Let's see what Anthropic has.

Bridgebench

16,715 次观看 • 4 个月前

I built a simple voice assistant in 70 lines of Python code. It uses: • LiveKit - The voice agent • AssemblyAI - To turn your voice into text • OpenAI - The brain of the agent, and to turn text into audio There's something really cool about this:

I built a simple voice assistant in 70 lines of Python code. It uses: • LiveKit - The voice agent • AssemblyAI - To turn your voice into text • OpenAI - The brain of the agent, and to turn text into audio There's something really cool about this:

Santiago

34,718 次观看 • 1 年前

AI coding tools are great at generating code. But can an AI agent take a vague idea, understand the whole project, make decisions, write the code, run it, test it, and actually turn it into something usable? I put EvoX Agent through a real-world task to find out. Here’s what happened ↓ #EvoxAgent #EvoMap #AlAgent

AI coding tools are great at generating code. But can an AI agent take a vague idea, understand the whole project, make decisions, write the code, run it, test it, and actually turn it into something usable? I put EvoX Agent through a real-world task to find out. Here’s what happened ↓ #EvoxAgent #EvoMap #AlAgent

Jay Bisen

71,887 次观看 • 21 天前

TURN CLAUDE CODE INTO AN AI SEO MACHINE. From content and keyword workflows to full search optimization, this is the kind of setup that can turn Claude into a real traffic engine.

TURN CLAUDE CODE INTO AN AI SEO MACHINE. From content and keyword workflows to full search optimization, this is the kind of setup that can turn Claude into a real traffic engine.

0xMarioNawfal

63,961 次观看 • 5 个月前

Claude Code tip, and it's absolute free f*cking gold: run Opus 5.5, Sonnet 5.5 and Fable 5.1 as one team and stop burning Opus tokens on routine work the setup in one line: plan on high, delegate on medium, keep Fable on call • who does what > Opus 5.5 on high - plans and ships the code > Sonnet 5.5 on medium - explorer reads code, worker edits and runs tests, researcher pulls docs > Fable 5.1 via /advisor fable - reads the whole session and speaks up only when it matters • when Fable 5.1 steps in -> before a plan: is this the right approach? -> when an error repeats: am I digging in the wrong place? -> before "done": what did I miss? Jev engineering takes it one layer lower: which file, which tool, retry or stop all go to Jev in under half a second, so the big models only see the real forks paste this into Claude Code ↓ "Rebuild my Claude Code setup: 1. Find subagents in ~/.claude/agents and .claude/agents that fit explorer, worker and researcher. Draft only the missing ones. Set each to model: sonnet, effort: medium. List any that pin a different model and leave them 2. In ~/.claude/settings.json set effortLevel to high and advisorModel to fable. 3. Report anything that disables the advisor (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, flag-fetching blockers) and CLAUDE_CODE_EFFORT_LEVEL. Change nothing. 4. Add to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done. Show every change as a diff. No edits until I say go." ↳

Claude Code tip, and it's absolute free f*cking gold: run Opus 5.5, Sonnet 5.5 and Fable 5.1 as one team and stop burning Opus tokens on routine work the setup in one line: plan on high, delegate on medium, keep Fable on call • who does what > Opus 5.5 on high - plans and ships the code > Sonnet 5.5 on medium - explorer reads code, worker edits and runs tests, researcher pulls docs > Fable 5.1 via /advisor fable - reads the whole session and speaks up only when it matters • when Fable 5.1 steps in -> before a plan: is this the right approach? -> when an error repeats: am I digging in the wrong place? -> before "done": what did I miss? Jev engineering takes it one layer lower: which file, which tool, retry or stop all go to Jev in under half a second, so the big models only see the real forks paste this into Claude Code ↓ "Rebuild my Claude Code setup: 1. Find subagents in ~/.claude/agents and .claude/agents that fit explorer, worker and researcher. Draft only the missing ones. Set each to model: sonnet, effort: medium. List any that pin a different model and leave them 2. In ~/.claude/settings.json set effortLevel to high and advisorModel to fable. 3. Report anything that disables the advisor (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, flag-fetching blockers) and CLAUDE_CODE_EFFORT_LEVEL. Change nothing. 4. Add to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done. Show every change as a diff. No edits until I say go." ↳

Mr. Buzzoni

139,098 次观看 • 1 天前

There's a built-in agent inside Claude Code you can invoke just by telling Claude to use the claude-code-guide agent Save this... you'll need it It's not a local file in your project. It's a built-in subagent defined in Claude Code's system itself. It answers questions about Claude Code CLI, the Agent SDK, and the Claude API. It uses Glob, Grep, Read, WebFetch, and WebSearch, but can't edit or write files. Its only job is to answer questions.

There's a built-in agent inside Claude Code you can invoke just by telling Claude to use the claude-code-guide agent Save this... you'll need it It's not a local file in your project. It's a built-in subagent defined in Claude Code's system itself. It answers questions about Claude Code CLI, the Agent SDK, and the Claude API. It uses Glob, Grep, Read, WebFetch, and WebSearch, but can't edit or write files. Its only job is to answer questions.

Daniel San

57,445 次观看 • 7 个月前

This is how Opus 5.5 in Claude Code built a WoW-style game in 36h. There's a lot more to it than one prompt. I wrote a detailed spec, gave it access to Unity, Blender and Higgsfield, and packed my own workflow into skills. I go through all of it in the video:

This is how Opus 5.5 in Claude Code built a WoW-style game in 36h. There's a lot more to it than one prompt. I wrote a detailed spec, gave it access to Unity, Blender and Higgsfield, and packed my own workflow into skills. I go through all of it in the video:

Stefan 3D AI

28,142 次观看 • 4 天前

I still don't think people understand what just happened with Claude Code. There is now one tool that takes you from a rough idea to fully designed, agency-tier, App Store-ready screens in minutes. One design system, every screen, real native code. Most builders hand design to Claude Code, get AI-default screens, and wonder why their app looks like every other vibe coded project. This is the 3-step workflow that fixes it: (full breakdown in the article)

I still don't think people understand what just happened with Claude Code. There is now one tool that takes you from a rough idea to fully designed, agency-tier, App Store-ready screens in minutes. One design system, every screen, real native code. Most builders hand design to Claude Code, get AI-default screens, and wonder why their app looks like every other vibe coded project. This is the 3-step workflow that fixes it: (full breakdown in the article)

Prajwal Tomar

146,206 次观看 • 3 个月前

THIS GUY CONNECTED CLAUDE VOICE MODE TO CLAUDE CODE AND NOW HE CODES BY TALKING INTO HIS AIRPODS while doing whatever he wants he uses Apple Reminders as a bridge between the two he talks into his AirPods, voice mode puts the prompt into a reminders list, Claude Code checks every 60 seconds and picks up the task AND it starts working on it back at his desk. walk outside. brainstorm with voice. code writes itself on your computer at home. he said he does his best thinking while walking and this lets him act on it instantly without pulling out his phone or sitting down. not a developer btw and he vibe coded the whole bridge system too. this is what hands-free vibe coding actually looks like

THIS GUY CONNECTED CLAUDE VOICE MODE TO CLAUDE CODE AND NOW HE CODES BY TALKING INTO HIS AIRPODS while doing whatever he wants he uses Apple Reminders as a bridge between the two he talks into his AirPods, voice mode puts the prompt into a reminders list, Claude Code checks every 60 seconds and picks up the task AND it starts working on it back at his desk. walk outside. brainstorm with voice. code writes itself on your computer at home. he said he does his best thinking while walking and this lets him act on it instantly without pulling out his phone or sitting down. not a developer btw and he vibe coded the whole bridge system too. this is what hands-free vibe coding actually looks like

Om Patel

151,333 次观看 • 5 个月前

people are actually using the little advent calendar app I vibe-coded my heart cannot handle this 😭🎄 had to upgrade my supabase storage bc it kinda exploded overnight

people are actually using the little advent calendar app I vibe-coded my heart cannot handle this 😭🎄 had to upgrade my supabase storage bc it kinda exploded overnight

marisa

339,037 次观看 • 10 个月前

Crazy that Claude can now autonomously code strategies and validate them on TradingView and it’s actually faster than my pipeline. Time to expand to a third platform for our code TradingView is next. 15+ strategies are waiting to be coded. And a full Meta EA TV version is coming. Probably only 0.001% of the industry is doing this. Huge thanks to Andrew and The Daily Profiler for this pipeline idea.

Crazy that Claude can now autonomously code strategies and validate them on TradingView and it’s actually faster than my pipeline. Time to expand to a third platform for our code TradingView is next. 15+ strategies are waiting to be coded. And a full Meta EA TV version is coming. Probably only 0.001% of the industry is doing this. Huge thanks to Andrew and The Daily Profiler for this pipeline idea.

ZenomTrader

98,972 次观看 • 6 个月前

Claude Sonnet 4.5 is now the default model for Augment Code. We’re rolling it out to all customers over the next 24 hours, where it will be available alongside Sonnet 4 (for a limited time) and GPT-5 in the model picker. Here’s how Sonnet 4.5 compares to Sonnet 4:

Claude Sonnet 4.5 is now the default model for Augment Code. We’re rolling it out to all customers over the next 24 hours, where it will be available alongside Sonnet 4 (for a limited time) and GPT-5 in the model picker. Here’s how Sonnet 4.5 compares to Sonnet 4:

Augment Code

29,603 次观看 • 1 年前

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 • 1 年前

got Claude Agent SDK working in Cloudflare Developers containers and built my own code fixer agent, check it out!👇 uses the github mcp/git cli/skills to clone the repo, understand, make the fix, and open a pr when done. planning on more agents focused on non-code tasks 👀

got Claude Agent SDK working in Cloudflare Developers containers and built my own code fixer agent, check it out!👇 uses the github mcp/git cli/skills to clone the repo, understand, make the fix, and open a pr when done. planning on more agents focused on non-code tasks 👀

Thomas Gauvin

18,454 次观看 • 9 个月前

ex-Anthropic engineer: "I left Anthropic to build agents systems in Google but nothing beats Claude as an agent yet - in coding and tool use, the rest are still behind " in this 90-min podcast, he showed how to build effective agent system with Claude from scratch to get into Anthropic, he hand-coded Karpathy's nanoGPT as a physicist Claude → tools → loops of verification → a real agent and why, at Google, he says Claude is the best watch & bookmark - then read the guide to agent systems ↓

ex-Anthropic engineer: "I left Anthropic to build agents systems in Google but nothing beats Claude as an agent yet - in coding and tool use, the rest are still behind " in this 90-min podcast, he showed how to build effective agent system with Claude from scratch to get into Anthropic, he hand-coded Karpathy's nanoGPT as a physicist Claude → tools → loops of verification → a real agent and why, at Google, he says Claude is the best watch & bookmark - then read the guide to agent systems ↓

codila

127,393 次观看 • 2 个月前

We rebuilt - entirely vibe coded with Claude Code & Opus 4.5. If this site was built manually, it would have cost over $50K. Instead, I was able to build it in 2 weeks with Claude Code. For the first time in our company's history, the marketing site isn't in Webflow. It's been live for 2 weeks. Nothing broke. Performance and vitals are perfect. AMA

We rebuilt - entirely vibe coded with Claude Code & Opus 4.5. If this site was built manually, it would have cost over $50K. Instead, I was able to build it in 2 weeks with Claude Code. For the first time in our company's history, the marketing site isn't in Webflow. It's been live for 2 weeks. Nothing broke. Performance and vitals are perfect. AMA

Julian Galluzzo

45,632 次观看 • 8 个月前

Creator of Claude Code : "I don't prompt Claude anymore. I create loops - and the loops do the work. My job is to create loops." In 30 minutes, Boris breaks down his real daily Claude Code setup. Claude + loops + routines + dynamic workflow Worth more than a $500 vibe-coding course

Creator of Claude Code : "I don't prompt Claude anymore. I create loops - and the loops do the work. My job is to create loops." In 30 minutes, Boris breaks down his real daily Claude Code setup. Claude + loops + routines + dynamic workflow Worth more than a $500 vibe-coding course

Codez

148,852 次观看 • 3 个月前