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。

Codex Dynamic workflows are great. Try it out. 1. Go to GitHub link below 2. Copy install instruction 3. Type /dynamic to invoke the skill Recreates the same orchestration logic as Claude Dynamic Workflows. > Generates orchestration script. > Spins up a swarm of subagents. > Enters /goal mode... show more

Dan McAteer

24,457 subscribers

127,717 次观看 • 11 天前 •via X (Twitter)

游戏教育科学技术

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

Claude Code has a new wild feature... dynamic workflow. How to try: set /model to opus 4.8 set /effort to "ultracode" 😂 use “workflow” in your prompt Claude will write an orchestration script, spawn subagents swarm, verify results, and report back.

Claude Code has a new wild feature... dynamic workflow. How to try: set /model to opus 4.8 set /effort to "ultracode" 😂 use “workflow” in your prompt Claude will write an orchestration script, spawn subagents swarm, verify results, and report back.

Min Choi

346,908 次观看 • 12 天前

Opus 4.8 is awesome but that's expected. The unsung hero of this release for me is dynamic workflows. Claude plans your task, fans it out to tens or hundreds of parallel subagents, verifies their work, and iterates until the results converge into one coordinated answer.

Opus 4.8 is awesome but that's expected. The unsung hero of this release for me is dynamic workflows. Claude plans your task, fans it out to tens or hundreds of parallel subagents, verifies their work, and iterates until the results converge into one coordinated answer.

Ado

152,409 次观看 • 12 天前

How to generate a Grokipedia shareable link? Just move your cursor next to the heading and press the copy link button. It will copy the dynamic shareable link to your clipboard.

How to generate a Grokipedia shareable link? Just move your cursor next to the heading and press the copy link button. It will copy the dynamic shareable link to your clipboard.

DogeDesigner

34,733 次观看 • 7 个月前

■ Dynamic Wallpaper "I can see it in your eyes... the same madness as mine." Click the link below to access the original wallpaper: #PathtoNowhere #PTN

■ Dynamic Wallpaper "I can see it in your eyes... the same madness as mine." Click the link below to access the original wallpaper: #PathtoNowhere #PTN

Path to Nowhere

14,709 次观看 • 11 天前

subagents are just recursive agents where you can apply different prompts + models depending on the task. since they’re just a primitive, Cursor cli can actually spawn subagents by calling cursor-agent in headless mode via shell commands. that’s what makes the cli so nice. you can extend it, experiment, and have a lot of fun exploring orchestration patterns. here’s one way to do it w. dynamic model selection: 1. create a subagents.mdc rule 2. drop in: ``` --- alwaysApply: true --- ALWAYS spawn subagents by running `cursor-agent -p [task] --output-format=text --force --model [model]` in the terminal. Each subagent should return a summary of the changes it made. Subagents should be used for ALL tasks You can adopt a fan-out pattern where you spawn subagents to perform parallel isolated tasks, and then fan-in the results. Use the following models: - `--model gpt-5` for reasoning, researching, and planning - `--model sonnet-4` for implementation ``` 3. start cursor cli and try it out you can also adjust the rule to be more explicit when it should use subagents, when not to, which models when etc.

subagents are just recursive agents where you can apply different prompts + models depending on the task. since they’re just a primitive, Cursor cli can actually spawn subagents by calling cursor-agent in headless mode via shell commands. that’s what makes the cli so nice. you can extend it, experiment, and have a lot of fun exploring orchestration patterns. here’s one way to do it w. dynamic model selection: 1. create a subagents.mdc rule 2. drop in: ``` --- alwaysApply: true --- ALWAYS spawn subagents by running `cursor-agent -p [task] --output-format=text --force --model [model]` in the terminal. Each subagent should return a summary of the changes it made. Subagents should be used for ALL tasks You can adopt a fan-out pattern where you spawn subagents to perform parallel isolated tasks, and then fan-in the results. Use the following models: - `--model gpt-5` for reasoning, researching, and planning - `--model sonnet-4` for implementation ``` 3. start cursor cli and try it out you can also adjust the rule to be more explicit when it should use subagents, when not to, which models when etc.

eric zakariasson

54,017 次观看 • 9 个月前

The world’s first AI-powered dynamic presentation tool. A next-generation AI dynamic presentation tool that completely outperforms traditional PPTs and older competitors. Boost efficiency with VoxDeck and completely replace traditional, cumbersome workflows.👇

The world’s first AI-powered dynamic presentation tool. A next-generation AI dynamic presentation tool that completely outperforms traditional PPTs and older competitors. Boost efficiency with VoxDeck and completely replace traditional, cumbersome workflows.👇

Alif Hossain

122,762 次观看 • 6 个月前

How to actually get the most out of Codex instead of bookmarking another great guide you’ll never open again: We turned this article into an interactive workbench. Before prompting Codex, open the workbench, choose your task type, and check whether you’re using the right Codex capabilities. Built by Codex inside Open Design. If you want the workbench, reply “Open Design” below and I’ll send it to you.

How to actually get the most out of Codex instead of bookmarking another great guide you’ll never open again: We turned this article into an interactive workbench. Before prompting Codex, open the workbench, choose your task type, and check whether you’re using the right Codex capabilities. Built by Codex inside Open Design. If you want the workbench, reply “Open Design” below and I’ll send it to you.

Open Design

60,553 次观看 • 19 天前

Bridgerton will try to duplicate this kind of newlywed dynamic with other couples, but they'll never have the same buzz as Kanthony

Bridgerton will try to duplicate this kind of newlywed dynamic with other couples, but they'll never have the same buzz as Kanthony

Pall ✨️

49,184 次观看 • 7 个月前

■ Dynamic Wallpaper (2/3） The sun will rise again tomorrow, and I'll be right here waiting for you. Click the link below to access the original wallpaper: #PathtoNowhere #PTN

■ Dynamic Wallpaper (2/3） The sun will rise again tomorrow, and I'll be right here waiting for you. Click the link below to access the original wallpaper: #PathtoNowhere #PTN

Path to Nowhere

13,881 次观看 • 10 个月前

Claude Code with: > Opus 4.8 > Ultracode > Dynamic Workflows > Auto-mode ON ...is amazing. This is the way. I only use it with my Enterprise account. On work that will return material value to my company. I'd use it in my personal account but I don't want my family to be destitute after one prompt.

Claude Code with: > Opus 4.8 > Ultracode > Dynamic Workflows > Auto-mode ON ...is amazing. This is the way. I only use it with my Enterprise account. On work that will return material value to my company. I'd use it in my personal account but I don't want my family to be destitute after one prompt.

Dan McAteer

72,585 次观看 • 5 天前

Next.js AI Chatbot now supports artifacts: • Dynamic code execution • Image generation • Spreadsheets • ... and more! Open-source and free to get started.

Next.js AI Chatbot now supports artifacts: • Dynamic code execution • Image generation • Spreadsheets • ... and more! Open-source and free to get started.

AI SDK

382,342 次观看 • 1 年前

I built a plugin to generate 3D assets directly from Codex, using the latest update that introduces image generation. It generates an image, calls the Tripo3D API, then starts an MCP server and a local viewer directly inside Codex. It uses the paid Tripo3D API (12 free generations, 600 credits included). Everything is open source on my GitHub. Link below. Feel free to contribute. Room for improvement: skeleton/animation support and multi-provider 3D support.

I built a plugin to generate 3D assets directly from Codex, using the latest update that introduces image generation. It generates an image, calls the Tripo3D API, then starts an MCP server and a local viewer directly inside Codex. It uses the paid Tripo3D API (12 free generations, 600 credits included). Everything is open source on my GitHub. Link below. Feel free to contribute. Room for improvement: skeleton/animation support and multi-provider 3D support.

Defend Intelligence (Anis Ayari)

11,934 次观看 • 1 个月前

Tension Map / Dynamic Squish 1. Geo Node to capture the distance between "Edge Vertices" node Position 1 & 2 as `before_edge_dist` 2. Curve modifier 3. Geo Node same again as `after_edge_dist`. `after_edge_dist / before_edge_dist = diff`. 4. Use the diff to mix normal maps

Tension Map / Dynamic Squish 1. Geo Node to capture the distance between "Edge Vertices" node Position 1 & 2 as `before_edge_dist` 2. Curve modifier 3. Geo Node same again as `after_edge_dist`. `after_edge_dist / before_edge_dist = diff`. 4. Use the diff to mix normal maps

snek3d

183,927 次观看 • 1 个月前

How To Buy $BUFFY (Simplified) 1. Install Tonkeeper wallet 2. Load it up with Ton ($TON) 3. Copy and paste the link below into your browser and connect 4. Enter the amount of $TON you would swap for $BUFFY

How To Buy $BUFFY (Simplified) 1. Install Tonkeeper wallet 2. Load it up with Ton ($TON) 3. Copy and paste the link below into your browser and connect 4. Enter the amount of $TON you would swap for $BUFFY

$BUFFY | Telegram Founder’s dog

45,787 次观看 • 2 年前

Claude Code Scheduled Tasks is now available... here's a solid idea to connect it with Telegram Save this so you don't forget to set it up! First, ask Claude to add a simple Telegram messaging module to your repo. You can use the Telegram Bot Builder Skill from Link: Install command: npx claude-code-templates@latest --skill enterprise-communication/telegram-bot-builder Once the module is in your project, grab your bot credentials from BotFather and add the bot ID to your .env file That's it! ✅ Now every Scheduled Task you create should end with an instruction for Claude to send the task result to Telegram using that module. Claude will handle the delivery automatically on every task it runs

Claude Code Scheduled Tasks is now available... here's a solid idea to connect it with Telegram Save this so you don't forget to set it up! First, ask Claude to add a simple Telegram messaging module to your repo. You can use the Telegram Bot Builder Skill from Link: Install command: npx claude-code-templates@latest --skill enterprise-communication/telegram-bot-builder Once the module is in your project, grab your bot credentials from BotFather and add the bot ID to your .env file That's it! ✅ Now every Scheduled Task you create should end with an instruction for Claude to send the task result to Telegram using that module. Claude will handle the delivery automatically on every task it runs

Daniel San

91,123 次观看 • 3 个月前

BIG LOWER BODY DAY - Big emphasis on the groin and hips prepping that area for some heavier Bulgarians and Belt Squats. 1. Dynamic Groin Drifts 2. Rolling Groin Rocks 3. Dynamic Copenhagens 4. Dynamic Lateral Squats

BIG LOWER BODY DAY - Big emphasis on the groin and hips prepping that area for some heavier Bulgarians and Belt Squats. 1. Dynamic Groin Drifts 2. Rolling Groin Rocks 3. Dynamic Copenhagens 4. Dynamic Lateral Squats

Vernon Griffith, CSCS*D

24,578 次观看 • 9 个月前

As a young and dynamic player, newly acquired forward Kaapo Kakko offers to bring skill and offense to the #SeaKraken at a critical point in the season. Geoff Baker breaks down today's trade →

As a young and dynamic player, newly acquired forward Kaapo Kakko offers to bring skill and offense to the #SeaKraken at a critical point in the season. Geoff Baker breaks down today's trade →

Seattle Kraken

89,944 次观看 • 1 年前

Opal, our no-code visual builder for AI workflows, just got a major upgrade. 🧠💎 We’ve added a new agent step that analyzes your goal, determines the best approach, and automatically calls the right tools — such as Veo for video or web search for research — to complete the task. We’re also adding new tools to make the agent even more capable: 💾 Memory – Remember info, like a user’s name or your style preferences across sessions. 🚀 Dynamic Routing – Let the agent choose the next best step using the “@ Go to” tool. 💬 Interactive Chat – Initiate user interactions to gather missing information or present options before moving on. Try it now →

Opal, our no-code visual builder for AI workflows, just got a major upgrade. 🧠💎 We’ve added a new agent step that analyzes your goal, determines the best approach, and automatically calls the right tools — such as Veo for video or web search for research — to complete the task. We’re also adding new tools to make the agent even more capable: 💾 Memory – Remember info, like a user’s name or your style preferences across sessions. 🚀 Dynamic Routing – Let the agent choose the next best step using the “@ Go to” tool. 💬 Interactive Chat – Initiate user interactions to gather missing information or present options before moving on. Try it now →

Google Labs

1,006,255 次观看 • 3 个月前

Introducing the playbooks skill security scanner. Checks all agent skill files for possible security risks before you install it. To try it out grab any GitHub URL to a SKILL.⁠md or skill folder, pop it in, hit enter:

Introducing the playbooks skill security scanner. Checks all agent skill files for possible security risks before you install it. To try it out grab any GitHub URL to a SKILL.⁠md or skill folder, pop it in, hit enter:

Ian Nuttall

26,057 次观看 • 4 个月前

Say goodbye to the limitations of the History API. Discover the Navigation API and unlock a new era of smooth, dynamic single-page applications. Check it out:

Say goodbye to the limitations of the History API. Discover the Navigation API and unlock a new era of smooth, dynamic single-page applications. Check it out:

Chrome for Developers

23,347 次观看 • 1 年前