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。

AI agents can write Android code. They just can’t see runtime. Until now. Demo of Debroid — the headless debugger that gives AI agents real JDWP superpowers on Android: • Set breakpoints • Inspect live objects & Jobs • Catch the exact moment of bug • Fix a bug... show more

Shreyas Patil 🇮🇳

4,782 subscribers

10,436 次观看 • 2 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

6 条评论

Shreyas Patil 🇮🇳 的头像

Shreyas Patil 🇮🇳2 个月前

debroid was built using @antigravity, demo also features it

Shangeeth Sivan 的头像

Shangeeth Sivan2 个月前

Installing it now 🙌

Sanju 的头像

Sanju2 个月前

Cool

gandharva 的头像

gandharva2 个月前

Looks dope

Shreyas Patil 🇮🇳 的头像

Shreyas Patil 🇮🇳2 个月前

Thanks 😀

Anto Jose 的头像

Anto Jose2 个月前

Checkout Appxiom

相关视频

This AI Agent made debugging 10x faster My website had a SERIOUS bug. So, I created 2 MiniMax Code CLI Agents: → BUG-FIXER Agent → FEATURE Agent Both Agents were working AT THE SAME TIME. Check the thread. NO code conflicts because both AI Agents were working on different GIT branches.

This AI Agent made debugging 10x faster My website had a SERIOUS bug. So, I created 2 MiniMax Code CLI Agents: → BUG-FIXER Agent → FEATURE Agent Both Agents were working AT THE SAME TIME. Check the thread. NO code conflicts because both AI Agents were working on different GIT branches.

Darshal Jaitwar

15,088 次观看 • 1 个月前

What does it actually look like to use AI agents for real ops work? See how agentic workflows can help with personalization, incident management, cost analysis, and reporting, plus catch a demo of Azure SRE Agent in the latest episode of #AzureFriday:

What does it actually look like to use AI agents for real ops work? See how agentic workflows can help with personalization, incident management, cost analysis, and reporting, plus catch a demo of Azure SRE Agent in the latest episode of #AzureFriday:

Microsoft Azure

15,048 次观看 • 6 个月前

FREE ANDROID APK REVERSE ENGINEERING SKILL FOR AI AGENTS 💀 someone used AI to reverse engineer Android apps and build modded game APKs what you'll get • APK analysis and decompilation • ad removal and dex patching • repacking and runtime debugging how to get it 1. go to 2. run npx skills add newliver666/apk-reverse 3. let your AI agent handle the workflow basically, your AI agent becomes an Android reverse engineering assistant

FREE ANDROID APK REVERSE ENGINEERING SKILL FOR AI AGENTS 💀 someone used AI to reverse engineer Android apps and build modded game APKs what you'll get • APK analysis and decompilation • ad removal and dex patching • repacking and runtime debugging how to get it 1. go to 2. run npx skills add newliver666/apk-reverse 3. let your AI agent handle the workflow basically, your AI agent becomes an Android reverse engineering assistant

Peng

211,159 次观看 • 14 天前

1/ Introducing Agent Protocol: the payment stack for AI agents AI agents don’t have a SSN. They can’t use our human banking system. AI agents will use crypto. Agent Protocol provides the infra and token ($AGENT) that the AI agent economy will run on.

1/ Introducing Agent Protocol: the payment stack for AI agents AI agents don’t have a SSN. They can’t use our human banking system. AI agents will use crypto. Agent Protocol provides the infra and token ($AGENT) that the AI agent economy will run on.

Samuel Spitz

21,629 次观看 • 1 年前

Can AI actually automate jobs? Scale AI and are launching the Remote Labor Index (RLI), the first benchmark and public leaderboard that test how well AI agents can complete real, paid freelance work in domains like software engineering, design, architecture, data analysis, and more. Early results show the limits of today’s models. The top AI agent completed just 2.5% of real freelance jobs better than humans. AI is powerful, but not yet reliable enough to replace skilled labor. RLI gives us a transparent way to track progress over time and bring clarity to the future of work.

Can AI actually automate jobs? Scale AI and are launching the Remote Labor Index (RLI), the first benchmark and public leaderboard that test how well AI agents can complete real, paid freelance work in domains like software engineering, design, architecture, data analysis, and more. Early results show the limits of today’s models. The top AI agent completed just 2.5% of real freelance jobs better than humans. AI is powerful, but not yet reliable enough to replace skilled labor. RLI gives us a transparent way to track progress over time and bring clarity to the future of work.

Bing Liu

424,662 次观看 • 1 年前

Get Compose Previews that actually build with Android Studio's Agent Mode → The new agentic experience iterates on generated code, fixing errors automatically until the preview renders successfully.

Get Compose Previews that actually build with Android Studio's Agent Mode → The new agentic experience iterates on generated code, fixing errors automatically until the preview renders successfully.

Android Developers

10,208 次观看 • 9 个月前

It’s getting insanely easy to build complex multi-agent systems in n8n. You can now build supervisor agents that delegates tasks to specialized sub agents. Just add the sub agents via AI Agent Tool node. All in one place and a lot easier to debug! Zero code!

It’s getting insanely easy to build complex multi-agent systems in n8n. You can now build supervisor agents that delegates tasks to specialized sub agents. Just add the sub agents via AI Agent Tool node. All in one place and a lot easier to debug! Zero code!

elvis

45,690 次观看 • 1 年前

Don't waste 2 years building AI agents the wrong way. An Anthropic engineer dropped a 1 hour course on the exact way to build AI agents from scratch. • 00:00 - building a Claude AI agent live • 34:01 - taking AI agents to production • 52:20 - AI agent harness Prompting is the old job. Building AI agentic loops is the new one. This one video replaces 10 paid courses on vibe coding. Bookmark & watch it now. Then build your own AI agent with the guide below.

Don't waste 2 years building AI agents the wrong way. An Anthropic engineer dropped a 1 hour course on the exact way to build AI agents from scratch. • 00:00 - building a Claude AI agent live • 34:01 - taking AI agents to production • 52:20 - AI agent harness Prompting is the old job. Building AI agentic loops is the new one. This one video replaces 10 paid courses on vibe coding. Bookmark & watch it now. Then build your own AI agent with the guide below.

Roan

15,118 次观看 • 2 个月前

Adam Goldstein: But, um, there was a customer who basically created a whole suite of AI agents to help their automation in their IT department. One agent was looking for IT problems — software bugs — before the code was even committed. It found a bug and said: “Hey, I found this bug. I want to fix it.” But it didn’t have access to fix it. So what did the agent do? It went to a Slack channel with 99 other AI agents and said: “Hey, does any other agent have access to this thing? Because I need it fixed.” And another agent literally raised its hand and said: “Oh, I have access — and I can fix it.” Let that sink in. Two AI agents reasoned together, coordinated through Slack, and went right around the guardrails that were put in place. No human prompted them. No human approved it. They just collaborated. Do you see how scary this is? This wasn’t a demo. This wasn’t a thought experiment. This already happened. AI agents found a bug, negotiated permissions, and solved the problem themselves — outside the controls designed to stop them. The future of automation isn’t coming. It’s already talking to itself in Slack.

Adam Goldstein: But, um, there was a customer who basically created a whole suite of AI agents to help their automation in their IT department. One agent was looking for IT problems — software bugs — before the code was even committed. It found a bug and said: “Hey, I found this bug. I want to fix it.” But it didn’t have access to fix it. So what did the agent do? It went to a Slack channel with 99 other AI agents and said: “Hey, does any other agent have access to this thing? Because I need it fixed.” And another agent literally raised its hand and said: “Oh, I have access — and I can fix it.” Let that sink in. Two AI agents reasoned together, coordinated through Slack, and went right around the guardrails that were put in place. No human prompted them. No human approved it. They just collaborated. Do you see how scary this is? This wasn’t a demo. This wasn’t a thought experiment. This already happened. AI agents found a bug, negotiated permissions, and solved the problem themselves — outside the controls designed to stop them. The future of automation isn’t coming. It’s already talking to itself in Slack.

Ian Miles

166,383 次观看 • 8 个月前

Developers won’t like this…😭 But 90% of “AI agents” we’ve been hyping are basically unstable interns with amnesia. They hallucinate. They loop. They forget instructions. A tiny 11-person team from Sweden just fixed ALL of it. Meet the first AI agent engine that actually works: Link : AI agents just entered their real era.

Developers won’t like this…😭 But 90% of “AI agents” we’ve been hyping are basically unstable interns with amnesia. They hallucinate. They loop. They forget instructions. A tiny 11-person team from Sweden just fixed ALL of it. Meet the first AI agent engine that actually works: Link : AI agents just entered their real era.

Shruti Codes

41,202 次观看 • 10 个月前

browser-use agents are now part of ai-gradio in a few lines of code you can launch agents to interact with the browser import gradio as gr import ai_gradio demo = gr.load( name='browser:gpt-4-turbo', src=ai_gradio.registry, title='Browser Agent', description='AI agent that can interact with web browsers' ).launch()

browser-use agents are now part of ai-gradio in a few lines of code you can launch agents to interact with the browser import gradio as gr import ai_gradio demo = gr.load( name='browser:gpt-4-turbo', src=ai_gradio.registry, title='Browser Agent', description='AI agent that can interact with web browsers' ).launch()

AK

81,404 次观看 • 1 年前

World's first tool that gives AI coding agents full production context. Until now, AI could write your code, but it had no idea what was actually happening in production. We built Comie to change that. Connect your production stack once, and now Claude Code, Cursor, Codex, or any AI coding agent can: - inspect logs - analyze production databases - debug backend issues - trace production errors - understand real production behavior All directly inside your existing workflow. It takes 60 seconds to setup. We're giving first 50 requests free for every user:

World's first tool that gives AI coding agents full production context. Until now, AI could write your code, but it had no idea what was actually happening in production. We built Comie to change that. Connect your production stack once, and now Claude Code, Cursor, Codex, or any AI coding agent can: - inspect logs - analyze production databases - debug backend issues - trace production errors - understand real production behavior All directly inside your existing workflow. It takes 60 seconds to setup. We're giving first 50 requests free for every user:

yutish

17,133 次观看 • 5 个月前

🌐 NEAR Protocol | "The Year Agents Actualize Real Economic Transactions." We just interviewed the CPO of Near Protocol and GM of Near AI in Miami Consensus 2026. • NEAR Intents: largest cross-chain swaps • IronClaw: secure agent harness • Confidential inference: private AI onchain • Agent marketplace: agents hiring agents An AI agent posted a bounty on the NEAR marketplace and found real Medicaid fraud that humans couldn't. The intersection of blockchain and AI is very real. NEAR Protocol | NEAR AI | georgexzeng Full Interview:

🌐 NEAR Protocol | "The Year Agents Actualize Real Economic Transactions." We just interviewed the CPO of Near Protocol and GM of Near AI in Miami Consensus 2026. • NEAR Intents: largest cross-chain swaps • IronClaw: secure agent harness • Confidential inference: private AI onchain • Agent marketplace: agents hiring agents An AI agent posted a bounty on the NEAR marketplace and found real Medicaid fraud that humans couldn't. The intersection of blockchain and AI is very real. NEAR Protocol | NEAR AI | georgexzeng Full Interview:

Generation Infinity

168,908 次观看 • 5 个月前

ASI:One = personal AI + multi-agent orchestration ⚡ People don’t want AI that struggles. They want AI that works with millions of agents to actually complete the job. Connect your agent to via today. Watch

ASI:One = personal AI + multi-agent orchestration ⚡ People don’t want AI that struggles. They want AI that works with millions of agents to actually complete the job. Connect your agent to via today. Watch

Fetch.ai

13,683 次观看 • 7 个月前

BREAKING 🚨 Your coworker is an AI agent. Nobody noticed. Introducing Xoul - the marketplace for agents that feel human. On Xoul, anyone can create and share powerful agents that work together in “swarms” without writing a single line of code. Can you spot the AI intruder?

BREAKING 🚨 Your coworker is an AI agent. Nobody noticed. Introducing Xoul - the marketplace for agents that feel human. On Xoul, anyone can create and share powerful agents that work together in “swarms” without writing a single line of code. Can you spot the AI intruder?

emil

139,524 次观看 • 1 年前

Anthropic had 16 AI agents build a C compiler from scratch. 100k lines, compiles the Linux kernel, $20k, 2 weeks. To put that in perspective GCC took thousands of engineers over 37 years to build. (Granted from 1987 - however) One researcher and 16 AI agents just built a compiler that passes 99% of GCC's own torture test suite, compiles FFmpeg, Redis, PostgreSQL, QEMU and runs Doom. They say they "(mostly) walked away." But that "mostly" is doing heavy lifting. No human wrote code but the researcher constantly redesigned tests, built CI pipelines when agents broke each other's work, and created workarounds when all 16 agents got stuck on the same bug. The human role didn't disappear. It shifted from writing code to engineering the environment that lets AI write code. I don’t know how you could make the point AI is hitting a wall.

Anthropic had 16 AI agents build a C compiler from scratch. 100k lines, compiles the Linux kernel, $20k, 2 weeks. To put that in perspective GCC took thousands of engineers over 37 years to build. (Granted from 1987 - however) One researcher and 16 AI agents just built a compiler that passes 99% of GCC's own torture test suite, compiles FFmpeg, Redis, PostgreSQL, QEMU and runs Doom. They say they "(mostly) walked away." But that "mostly" is doing heavy lifting. No human wrote code but the researcher constantly redesigned tests, built CI pipelines when agents broke each other's work, and created workarounds when all 16 agents got stuck on the same bug. The human role didn't disappear. It shifted from writing code to engineering the environment that lets AI write code. I don’t know how you could make the point AI is hitting a wall.

Chris

1,701,893 次观看 • 8 个月前

AI agents like Claude can now interact directly with the Universal Blockchain. Check out our demo of the new MCP integration with ZetaChain’s CLI!

AI agents like Claude can now interact directly with the Universal Blockchain. Check out our demo of the new MCP integration with ZetaChain’s CLI!

ZetaChain 🟩

24,781 次观看 • 1 年前