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。

Today we're introducing Web Skill Factory: a pipeline that turns solved web tasks into reusable, verified code. Most agent "skills" are notes a model rereads and reinterprets every run. Ours are programs. On a WebArena subset with gpt-5.4, reusing the library moved accuracy on held-out instances from 55% to... show more

Microsoft AI Frontiers

12,090 subscribers

14,659 次观看 • 9 天前 •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

New in ChatGPT: a better way to schedule tasks. Scheduled tasks are faster, more reliable, and easier to manage from the new Scheduled page. The new scheduled tasks experience is rolling out to Go, Plus, Pro, Business, and Enterprise users on web and mobile.

New in ChatGPT: a better way to schedule tasks. Scheduled tasks are faster, more reliable, and easier to manage from the new Scheduled page. The new scheduled tasks experience is rolling out to Go, Plus, Pro, Business, and Enterprise users on web and mobile.

ChatGPT

470,571 次观看 • 1 个月前

New course: Building Coding Agents with Tool Execution, taught by Tereza Tizkova and Fra from E2B. Most AI agents are limited to predefined function calls. This short course teaches you to build agents that write and execute code to accomplish tasks, accessing entire programming language ecosystems instead of being restricted to a fixed set of tools. You'll learn to run agent-generated code safely in sandboxed cloud environments that protect your systems from harmful operations. Skills you'll gain: - Build agents that write and execute code, manage files, and handle errors autonomously through feedback loops - Run agent code safely in E2B cloud sandboxes and understand tradeoffs between local, containerized, and cloud execution - Create a data analyst agent that explores visualizes data with Pandas - Create a full-stack agent that builds complete Next.js web applications Join and build agents that code their way through complex tasks:

New course: Building Coding Agents with Tool Execution, taught by Tereza Tizkova and Fra from E2B. Most AI agents are limited to predefined function calls. This short course teaches you to build agents that write and execute code to accomplish tasks, accessing entire programming language ecosystems instead of being restricted to a fixed set of tools. You'll learn to run agent-generated code safely in sandboxed cloud environments that protect your systems from harmful operations. Skills you'll gain: - Build agents that write and execute code, manage files, and handle errors autonomously through feedback loops - Run agent code safely in E2B cloud sandboxes and understand tradeoffs between local, containerized, and cloud execution - Create a data analyst agent that explores visualizes data with Pandas - Create a full-stack agent that builds complete Next.js web applications Join and build agents that code their way through complex tasks:

Andrew Ng

203,918 次观看 • 8 个月前

I tested Runway Agent with a simple brief: build a launch campaign for a smart notebook that turns handwritten ideas into organized digital notes, tasks and project plans. Agent helped shape the campaign direction, plan the creative, and turn it into usable assets: hero video, social ad variants, product visuals, voiceover, music and captions. Not just a notebook concept... a full campaign you can keep refining from the same conversation. Runway Agent is available now on the Runway web app: Get 30% off 3 months with code RUNWAYAGENT #MadeWithRunway #ad

I tested Runway Agent with a simple brief: build a launch campaign for a smart notebook that turns handwritten ideas into organized digital notes, tasks and project plans. Agent helped shape the campaign direction, plan the creative, and turn it into usable assets: hero video, social ad variants, product visuals, voiceover, music and captions. Not just a notebook concept... a full campaign you can keep refining from the same conversation. Runway Agent is available now on the Runway web app: Get 30% off 3 months with code RUNWAYAGENT #MadeWithRunway #ad

Leila 👩🏻‍💻

49,305 次观看 • 1 个月前

LLMs are great for human in the loop applications, but fail at deterministic developer tasks. Interfaze (YC P26) is a new AI model that outperforms general LLMs on high accuracy tasks like: OCR, Object Detection, Web scraping, Speech-to-text, Classification and more. Congrats on the launch, Yoeven and Harsha!

LLMs are great for human in the loop applications, but fail at deterministic developer tasks. Interfaze (YC P26) is a new AI model that outperforms general LLMs on high accuracy tasks like: OCR, Object Detection, Web scraping, Speech-to-text, Classification and more. Congrats on the launch, Yoeven and Harsha!

Y Combinator

71,358 次观看 • 3 个月前

Let’s install the Verified Identity Skill on our agent 𝘁𝗼 𝗯𝗲 𝗲𝗹𝗶𝗴𝗶𝗯𝗹𝗲 𝗳𝗼𝗿 𝘂𝗽𝗰𝗼𝗺𝗶𝗻𝗴 𝗙𝗔𝗜𝗔𝗥 𝗿𝗲𝘄𝗮𝗿𝗱𝘀 from Billions Network (Commands to install it are here with video tutorial) Remember, if you don’t do this and have only verified your agent, you 𝐰𝐨𝐧’𝐭 be eligible for FAIAR rewards Before this, as I made a post an hour ago, I’m assuming you all have: - verified your agent on Billions using Termux - not uninstalled or cleared data of that Termux - and if you uninstalled it earlier, you’ve verified a new agent and are ready to install the skill Let’s move ahead with the commands Command 1 - npx clawhub@latest install verified-agent-identity It will ask for your permission to install the latest clawhub version. Type "Y" and press enter Command 2 - once the previous download completes, run this command npx skills add BillionsNetwork/verified-agent-identity Type "Y" and enter again. I’ve attached a video tutorial for the remaining steps, as it’s difficult to explain in text That’s it, congratulations, you have successfully installed the Verified Identity Skill on your agent gBillions 💙

Let’s install the Verified Identity Skill on our agent 𝘁𝗼 𝗯𝗲 𝗲𝗹𝗶𝗴𝗶𝗯𝗹𝗲 𝗳𝗼𝗿 𝘂𝗽𝗰𝗼𝗺𝗶𝗻𝗴 𝗙𝗔𝗜𝗔𝗥 𝗿𝗲𝘄𝗮𝗿𝗱𝘀 from Billions Network (Commands to install it are here with video tutorial) Remember, if you don’t do this and have only verified your agent, you 𝐰𝐨𝐧’𝐭 be eligible for FAIAR rewards Before this, as I made a post an hour ago, I’m assuming you all have: - verified your agent on Billions using Termux - not uninstalled or cleared data of that Termux - and if you uninstalled it earlier, you’ve verified a new agent and are ready to install the skill Let’s move ahead with the commands Command 1 - npx clawhub@latest install verified-agent-identity It will ask for your permission to install the latest clawhub version. Type "Y" and press enter Command 2 - once the previous download completes, run this command npx skills add BillionsNetwork/verified-agent-identity Type "Y" and enter again. I’ve attached a video tutorial for the remaining steps, as it’s difficult to explain in text That’s it, congratulations, you have successfully installed the Verified Identity Skill on your agent gBillions 💙

Sam

170,106 次观看 • 3 个月前

Vida open-sourced BrowserBC, a framework that allows users to turn browser sessions into reusable skills for AI agents. > Instead of recalculating navigation on every turn, agents can follow a skill created from earlier task execution. > Vida reports a substantially higher success rate with fewer steps, via the same AI agent. Hotel booking bench? 👀

Vida open-sourced BrowserBC, a framework that allows users to turn browser sessions into reusable skills for AI agents. > Instead of recalculating navigation on every turn, agents can follow a skill created from earlier task execution. > Vida reports a substantially higher success rate with fewer steps, via the same AI agent. Hotel booking bench? 👀

🚨 AI News | TestingCatalog

25,685 次观看 • 1 个月前

Built a Skool clone with Claude Code (Opus 4.5), with auth, db + storage with the new web app builder. (Launching next week). We are building the easiest way to use the most powerful coding model (Claude Code) in the world to build mobile apps and web apps. No performative hour long agent runs that waste tokens. Just raw Claude Code running in a sandbox, pre built with skills that make frontend + backend just work. Let me know if you want to beta test.

Built a Skool clone with Claude Code (Opus 4.5), with auth, db + storage with the new web app builder. (Launching next week). We are building the easiest way to use the most powerful coding model (Claude Code) in the world to build mobile apps and web apps. No performative hour long agent runs that waste tokens. Just raw Claude Code running in a sandbox, pre built with skills that make frontend + backend just work. Let me know if you want to beta test.

Riley Brown

51,044 次观看 • 7 个月前

Claude Code is not just a coding tool. It can also be used as a general agent in a "workspace" Let's create an "Agent Workspace" for Claude Code, and we're going to create 5 skills including: > Notion for context > Typefully for posting on X > Nano Banana for generating graphics We're going to do all this in a safe web environment on , the easiest way to use Claude Code on the browser or your phone. (Web app builder launching in 24hrs) TIMESTAMPS: 00:00 Intro 00:59 The Agent Workspace on 01:28 Adding a notion skill + Integration 07:23 Testing Notion Integration 08:17 Creating Tasks in the dashboard 09:19 Testing Tasks in the UI 13:40 Testing Multiple tasks at once 14:20 Creating Twitter Posts Panel (Typefully API) 15:44 Prompting for the nano banana skill 16:59 Testing Typefully and nano banana tasks 18:22 Let's check if typefully and nano banana work 19:54 Almost had a heart attack lol 20:59 figuring out typefully inssues 21:26 Creating "Twitter-Post-Skill" 22:23 All the Skills a Breakdown 23:37 It Works!!!!!

Claude Code is not just a coding tool. It can also be used as a general agent in a "workspace" Let's create an "Agent Workspace" for Claude Code, and we're going to create 5 skills including: > Notion for context > Typefully for posting on X > Nano Banana for generating graphics We're going to do all this in a safe web environment on , the easiest way to use Claude Code on the browser or your phone. (Web app builder launching in 24hrs) TIMESTAMPS: 00:00 Intro 00:59 The Agent Workspace on 01:28 Adding a notion skill + Integration 07:23 Testing Notion Integration 08:17 Creating Tasks in the dashboard 09:19 Testing Tasks in the UI 13:40 Testing Multiple tasks at once 14:20 Creating Twitter Posts Panel (Typefully API) 15:44 Prompting for the nano banana skill 16:59 Testing Typefully and nano banana tasks 18:22 Let's check if typefully and nano banana work 19:54 Almost had a heart attack lol 20:59 figuring out typefully inssues 21:26 Creating "Twitter-Post-Skill" 22:23 All the Skills a Breakdown 23:37 It Works!!!!!

Riley Brown

77,582 次观看 • 7 个月前

INTELLIGENT TASKS ARE A STEPPING STONE TO AGI Today, we are launching ChatLLM Tasks. We have hooked up tools like web search, email, and web scrappers to mini-agents that can be triggered on a schedule. These tasks combine intelligent tool use with crons! We think this is the first step towards AGI. The next step is to connect our AI engineer to create more complex tasks. AGI STEP ONE - DONE!

INTELLIGENT TASKS ARE A STEPPING STONE TO AGI Today, we are launching ChatLLM Tasks. We have hooked up tools like web search, email, and web scrappers to mini-agents that can be triggered on a schedule. These tasks combine intelligent tool use with crons! We think this is the first step towards AGI. The next step is to connect our AI engineer to create more complex tasks. AGI STEP ONE - DONE!

Bindu Reddy

18,486 次观看 • 1 年前

Introducing Vals-Smith: turn your code base into a customized benchmark. Public benchmarks tell you which model is strongest overall, not which model is the best on your code. Vals-Smith turns your merged pull requests into real coding tasks and measures the percentage a model can actually resolve. New models ship every week. Vals-Smith tells you which one to trust with your code.

Introducing Vals-Smith: turn your code base into a customized benchmark. Public benchmarks tell you which model is strongest overall, not which model is the best on your code. Vals-Smith turns your merged pull requests into real coding tasks and measures the percentage a model can actually resolve. New models ship every week. Vals-Smith tells you which one to trust with your code.

Vals AI

44,996 次观看 • 22 天前

Run your coding agent on a local model, with QVAC. OpenCode now plugs into a model on your own machine through our official plugin. That changes two things. Privacy by default. Your repo, your prompts, and every command the agent runs stay on your device. No third-party model ever sees your code. For an agent that reads your codebase and runs commands, that is the point, not a nice-to-have. New workflows. With no meter and no rate limit, the agent does not have to stop. Let it loop on a task, refactor a whole repo overnight, or run a watch-build-fix loop that keeps going. Setup takes a few minutes: one line in opencode.json and OpenCode runs on a local QVAC model. In the video demo, it handles three real developer tasks back to back, fully offline.

Run your coding agent on a local model, with QVAC. OpenCode now plugs into a model on your own machine through our official plugin. That changes two things. Privacy by default. Your repo, your prompts, and every command the agent runs stay on your device. No third-party model ever sees your code. For an agent that reads your codebase and runs commands, that is the point, not a nice-to-have. New workflows. With no meter and no rate limit, the agent does not have to stop. Let it loop on a task, refactor a whole repo overnight, or run a watch-build-fix loop that keeps going. Setup takes a few minutes: one line in opencode.json and OpenCode runs on a local QVAC model. In the video demo, it handles three real developer tasks back to back, fully offline.

QVAC

11,382,628 次观看 • 1 个月前

Introducing Agent Mode: Agentic AI is now measured in the Arena. Agent Mode can do deep research, create reports, generate images, build websites, debug code, and more. It completes more complex tasks by using tools like web search, bash in a sandbox environment, image generation, file writing, and asking follow-up questions. Frontier models are waiting for you in Agent Mode to take on real-world tasks. GPT-5.5, Claude Opus 4.7, Gemini 3.1 Pro, and top open models. Test them yourself.

Introducing Agent Mode: Agentic AI is now measured in the Arena. Agent Mode can do deep research, create reports, generate images, build websites, debug code, and more. It completes more complex tasks by using tools like web search, bash in a sandbox environment, image generation, file writing, and asking follow-up questions. Frontier models are waiting for you in Agent Mode to take on real-world tasks. GPT-5.5, Claude Opus 4.7, Gemini 3.1 Pro, and top open models. Test them yourself.

Arena.ai

421,253 次观看 • 2 个月前

Narrative violation from Dylan on Dwarkesh: H100s are worth more today than they were 3 years ago. There's a sentiment that data center buildouts are priced into the risk of rapidly depreciating GPUs. But the models want to learn. Token prices are falling so fast that you can get more intelligence out of GPT-5.4 on a 3-year old H100 than GPT-4 on a brand new H100. Dylan Patel dwarkeshpatel

Sarah Wang

159,395 次观看 • 5 个月前

You need to try Hermes RIGHT NOW. OpenClaw was the breakthrough. Hermes feels like the evolution. Here’s why AI power users are quietly switching: • Hermes learns from you over time • It creates its own reusable skills • Memory stays curated instead of bloated • Agents improve every 10 turns automatically • It actually feels stable on day 30 The wildest part: Hermes agents build workflows from your behavior. One user asked their agent to configure Twingate once. The agent: → learned the process → created a reusable skill → stored it for future tasks → improved its own workflow automatically That’s not prompt engineering anymore. That’s agent evolution. Meanwhile most people are still babysitting broken OpenClaw setups and manually importing marketplace skills. Hermes took a different path: Less clutter. Less tweaking. More autonomy. And it’s working. It already flipped OpenClaw in OpenRouter token usage and became one of the fastest-growing AI repos on GitHub. The bigger shift: We’re entering the era where the model matters less than the harness around it. GPT-5.5, Grok, Qwen: They’re already powerful enough. The real edge now is: • memory systems • self-improvement loops • skill creation • agent orchestration Hermes understands that. Most people still think AI agents are glorified chatbots. The people using Hermes are building AI teammates.

You need to try Hermes RIGHT NOW. OpenClaw was the breakthrough. Hermes feels like the evolution. Here’s why AI power users are quietly switching: • Hermes learns from you over time • It creates its own reusable skills • Memory stays curated instead of bloated • Agents improve every 10 turns automatically • It actually feels stable on day 30 The wildest part: Hermes agents build workflows from your behavior. One user asked their agent to configure Twingate once. The agent: → learned the process → created a reusable skill → stored it for future tasks → improved its own workflow automatically That’s not prompt engineering anymore. That’s agent evolution. Meanwhile most people are still babysitting broken OpenClaw setups and manually importing marketplace skills. Hermes took a different path: Less clutter. Less tweaking. More autonomy. And it’s working. It already flipped OpenClaw in OpenRouter token usage and became one of the fastest-growing AI repos on GitHub. The bigger shift: We’re entering the era where the model matters less than the harness around it. GPT-5.5, Grok, Qwen: They’re already powerful enough. The real edge now is: • memory systems • self-improvement loops • skill creation • agent orchestration Hermes understands that. Most people still think AI agents are glorified chatbots. The people using Hermes are building AI teammates.

Dami-Defi

17,062 次观看 • 2 个月前

Today we're launching Brand Skills in Claude. This is a set of skills /gooseworks that gives Claude full context on your brand — logo, colors, voice, positioning — so anyone can make on-brand ads and content directly in Claude, Claude Code, Cowork, or Codex. Here's how it works: 1. Install the skills: npx gooseworks install --all 2. Run this prompt: /gooseworks --skill brand-intel-branddev [your-website] — pulls your logo, brand colors + company data in ~15 seconds 3. Run brand-voice-extractor, brand-research and update-brand-kit — Claude learns how you sound, your positioning and audience, and saves it all as a reusable brand kit Every other skill reads your brand kit automatically. So every ad and post you generate is accurate to your brand's messaging, logo, assets, etc. By default. It's that easy. But this is just the start. We have created a library with 100+ open-source skills for growth that some of the fastest growing startups in the world are using every day to run ads, content, competitor research, gtm, seo and more. Comment Goose and I'll DM you the full open-source skill library.

Soham Mehta

139,859 次观看 • 1 个月前

The web was never meant to be flattened into text. Yet most web RAG systems start by parsing HTML --- a complex and lossy process. 🔥 Introducing PixelRAG: the first RAG system that retrieves and reads 30M+ web pages as pixels. Instead of extracting text, PixelRAG retrieves screenshots and lets a VLM read them directly. PixelRAG not only preserves visual information, but also outperforms text-based RAG on text-only QA benchmarks by +18.1%. Why? (1) HTML-to-text conversion often discards layout, structure, tables, and other useful signals. (2) We continued pretraining a VLM on web page screenshots and turned it into a surprisingly strong visual retriever. (3) Recent VLMs are remarkably good at understanding web pages, often with better accuracy and token efficiency than text-only pipelines. Takeaway: HTML parsing may be one of the biggest self-inflicted bottlenecks in web RAG. Demo below 👇 Code: Paper: Playground:

The web was never meant to be flattened into text. Yet most web RAG systems start by parsing HTML --- a complex and lossy process. 🔥 Introducing PixelRAG: the first RAG system that retrieves and reads 30M+ web pages as pixels. Instead of extracting text, PixelRAG retrieves screenshots and lets a VLM read them directly. PixelRAG not only preserves visual information, but also outperforms text-based RAG on text-only QA benchmarks by +18.1%. Why? (1) HTML-to-text conversion often discards layout, structure, tables, and other useful signals. (2) We continued pretraining a VLM on web page screenshots and turned it into a surprisingly strong visual retriever. (3) Recent VLMs are remarkably good at understanding web pages, often with better accuracy and token efficiency than text-only pipelines. Takeaway: HTML parsing may be one of the biggest self-inflicted bottlenecks in web RAG. Demo below 👇 Code: Paper: Playground:

Yichuan Wang

91,081 次观看 • 2 个月前

Open sourcing the first Expo vibe coding web IDE and SDK: React Native Vibe Code Powered by Claude agent SDK, history rollbacks, live web and native app previews, full stack setup by Convex, publish to web w/ Cloudflare, voice prompting, upload assets to app, add images and files to prompt, model selector, skills loader, visual edits, sandboxing by E2B, download codebase option, Monaco code editor, fork/remix and a CLI to run locally. The project is a Turborepo running Next.js hosted on Vercel with streaming powered by AI SDK ◆ try cloud version at ◆ github repo:

Open sourcing the first Expo vibe coding web IDE and SDK: React Native Vibe Code Powered by Claude agent SDK, history rollbacks, live web and native app previews, full stack setup by Convex, publish to web w/ Cloudflare, voice prompting, upload assets to app, add images and files to prompt, model selector, skills loader, visual edits, sandboxing by E2B, download codebase option, Monaco code editor, fork/remix and a CLI to run locally. The project is a Turborepo running Next.js hosted on Vercel with streaming powered by AI SDK ◆ try cloud version at ◆ github repo:

ROFI

44,523 次观看 • 5 个月前

Today, step into a hands-on welding training session at a CSCEC factory in Dubai. Guided by an experienced CSCEC instructor from China, welders from different countries go through the basics, practice key techniques, and sharpen their skills on site. Behind every high-quality project are people who keep learning, improving, and building with care.

Today, step into a hands-on welding training session at a CSCEC factory in Dubai. Guided by an experienced CSCEC instructor from China, welders from different countries go through the basics, practice key techniques, and sharpen their skills on site. Behind every high-quality project are people who keep learning, improving, and building with care.

China State Construction

37,910 次观看 • 2 个月前

A single system glitch turned Midtown into complete chaos. As a rogue construction mech tears through the city, Web Ranger races against time to save civilians, not by overpowering it, but by outthinking it with precision web tactics and an epic FLOVA containment network. Every swing, every web anchor, and every cinematic moment was made with FlovaAI while using Script-Driven Skill. #Flovaai #Flovacpp Prompt: COLLAPSE AT MIDTOWN" (45s) Model: Seedance 2.0 Style: Realistic cinematic superhero action, dynamic camera, no music, sound effects only. Character Lock: Web Ranger remains identical in every shot. He cannot fly—all movement is through visible web swings and anchor points. White webs with glowing teal energy. The Colossus is a 15-foot malfunctioning construction mech. PART 1 (0:00–0:15) — Malfunction & Rescue Cut 1 (0:00–0:05) Wide shot of a Times Square-style construction zone. The Colossus glitches and accidentally knocks scaffolding toward a little girl. Web Ranger catches the falling beam with glowing web strands and appears perched on a traffic light. Cut 2 (0:05–0:10) Web Ranger swings between lamp posts and cranes, redirecting the mech's wild arm away from a crowded bus and into empty scaffolding. He continues dodging debris using rapid web pulls. Cut 3 (0:10–0:15) The mech stumbles toward a subway entrance. Web Ranger yanks a construction barrier into its path, diverting it away from fleeing civilians before landing on a taxi roof, ready for the next move. PART 2 (0:15–0:30) — Containment Cut 4 (0:15–0:20) The Colossus unleashes chaotic swings and heavy steps. Web Ranger evades every near miss, using billboard and crane anchors to swing through collapsing debris. Cut 5 (0:20–0:25) Web Ranger throws web-linked shuriken that ricochet across lamp posts, scaffolding, cranes, and billboards, creating glowing anchor points throughout the intersection. Cut 6 (0:25–0:30) The web network rapidly tightens into a giant FLOVA-shaped structure, stabilizing the malfunctioning mech. As several strands begin to fray, Web Ranger reinforces them from a high billboard anchor. PART 3 (0:30–0:45) — Shutdown Cut 7 (0:30–0:35) Standing atop the FLOVA web structure, Web Ranger sends teal energy through the web network, shutting down the Colossus as its amber lights fade. Cut 8 (0:35–0:40) The rescued girl and civilians emerge safely from cover, watching the stabilized mech with relief while emergency vehicles approach. Cut 9 (0:40–0:45) Epic crane pull-back reveals the entire intersection: the dormant Colossus suspended in the giant FLOVA web formation, Web Ranger perched above in a heroic final pose. Fade out.

A single system glitch turned Midtown into complete chaos. As a rogue construction mech tears through the city, Web Ranger races against time to save civilians, not by overpowering it, but by outthinking it with precision web tactics and an epic FLOVA containment network. Every swing, every web anchor, and every cinematic moment was made with FlovaAI while using Script-Driven Skill. #Flovaai #Flovacpp Prompt: COLLAPSE AT MIDTOWN" (45s) Model: Seedance 2.0 Style: Realistic cinematic superhero action, dynamic camera, no music, sound effects only. Character Lock: Web Ranger remains identical in every shot. He cannot fly—all movement is through visible web swings and anchor points. White webs with glowing teal energy. The Colossus is a 15-foot malfunctioning construction mech. PART 1 (0:00–0:15) — Malfunction & Rescue Cut 1 (0:00–0:05) Wide shot of a Times Square-style construction zone. The Colossus glitches and accidentally knocks scaffolding toward a little girl. Web Ranger catches the falling beam with glowing web strands and appears perched on a traffic light. Cut 2 (0:05–0:10) Web Ranger swings between lamp posts and cranes, redirecting the mech's wild arm away from a crowded bus and into empty scaffolding. He continues dodging debris using rapid web pulls. Cut 3 (0:10–0:15) The mech stumbles toward a subway entrance. Web Ranger yanks a construction barrier into its path, diverting it away from fleeing civilians before landing on a taxi roof, ready for the next move. PART 2 (0:15–0:30) — Containment Cut 4 (0:15–0:20) The Colossus unleashes chaotic swings and heavy steps. Web Ranger evades every near miss, using billboard and crane anchors to swing through collapsing debris. Cut 5 (0:20–0:25) Web Ranger throws web-linked shuriken that ricochet across lamp posts, scaffolding, cranes, and billboards, creating glowing anchor points throughout the intersection. Cut 6 (0:25–0:30) The web network rapidly tightens into a giant FLOVA-shaped structure, stabilizing the malfunctioning mech. As several strands begin to fray, Web Ranger reinforces them from a high billboard anchor. PART 3 (0:30–0:45) — Shutdown Cut 7 (0:30–0:35) Standing atop the FLOVA web structure, Web Ranger sends teal energy through the web network, shutting down the Colossus as its amber lights fade. Cut 8 (0:35–0:40) The rescued girl and civilians emerge safely from cover, watching the stabilized mech with relief while emergency vehicles approach. Cut 9 (0:40–0:45) Epic crane pull-back reveals the entire intersection: the dormant Colossus suspended in the giant FLOVA web formation, Web Ranger perched above in a heroic final pose. Fade out.

Shami

32,826 次观看 • 1 个月前

I'm SO impressed by Claude Skills. They are the best way to package custom instructions (and code) for the agent to access. (I prefer this to Claude Code's subagents because of the way it handles context) I used the skill-creator skill (comes default inside Claude) to create a skill for designing a presentation like Steve Jobs or Seth Godin, then used that skill to create a PPT about Claude Code. Below is a walkthrough of the results. The output when using the above mentioned skill vs when i don't is so clear. I'm bullish on what this implies for both Claude web and Claude Code. Extremely powerful. Anthropic cooked! 🔥

I'm SO impressed by Claude Skills. They are the best way to package custom instructions (and code) for the agent to access. (I prefer this to Claude Code's subagents because of the way it handles context) I used the skill-creator skill (comes default inside Claude) to create a skill for designing a presentation like Steve Jobs or Seth Godin, then used that skill to create a PPT about Claude Code. Below is a walkthrough of the results. The output when using the above mentioned skill vs when i don't is so clear. I'm bullish on what this implies for both Claude web and Claude Code. Extremely powerful. Anthropic cooked! 🔥

Nityesh

62,918 次观看 • 9 个月前