Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Our agent autonomously found this kernel 0day and its exploit works on the #KCTF target. We are building to find vulnerabilities systematically, not just shadow bugs. See the quoted post below—comment "depthfirst" and we'll send you a free agent to try out.

Markak_'s profile picture

Zhenpeng (Leo) Lin

3,343 subscribers

16,741 görüntüleme • 3 ay önce •via X (Twitter)

#KCTF
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

⭐ BIG NEWS ⭐ AI Agent creation and automation are now free and open to everyone! Build your own personalized AI agent and let it run autonomously on your Twitter/X account! Try it now!
0:12

⭐ BIG NEWS ⭐ AI Agent creation and automation are now free and open to everyone! Build your own personalized AI agent and let it run autonomously on your Twitter/X account! Try it now!

Hedgecast Fun

71,078 görüntüleme • 1 yıl önce

🚨 CodeRabbit releases its AI agent in major coding tools. You can now use Cursor or Windsurf for coding, and let CodeRabbit’s AI agent help you debug and find security vulnerabilities. Free AI code reviews directly in the IDE. Here’s how:
0:19

🚨 CodeRabbit releases its AI agent in major coding tools. You can now use Cursor or Windsurf for coding, and let CodeRabbit’s AI agent help you debug and find security vulnerabilities. Free AI code reviews directly in the IDE. Here’s how:

Alvaro Cintas

53,198 görüntüleme • 1 yıl önce

Our Fine-Tuned AI SDR has booked this client over 75 qualified sales appointments in the 7 days alone. With average close rate of 22% and a ticket price of $6500, that's an additional $107,250 in revenue. There are a lot of businesses that are wasting thousands and thousands of dollars a month on "appointment setters".... We live in 2025, you can leverage AI Agents to fully qualify, converse, and book appointments for you. Comment the word "Setter" down below and I'll send you a free guide that show's how this agent works.
0:14

Our Fine-Tuned AI SDR has booked this client over 75 qualified sales appointments in the 7 days alone. With average close rate of 22% and a ticket price of $6500, that's an additional $107,250 in revenue. There are a lot of businesses that are wasting thousands and thousands of dollars a month on "appointment setters".... We live in 2025, you can leverage AI Agents to fully qualify, converse, and book appointments for you. Comment the word "Setter" down below and I'll send you a free guide that show's how this agent works.

Nate Sroor

93,283 görüntüleme • 1 yıl önce

Today we’re introducing Google AI Threat Defense - a comprehensive AI-powered cybersecurity solution designed to help continuously monitor for and stop AI-powered threats before they can impact your business. Here’s how it works: 1. AI Threat Defense uses our cybersecurity platform Wiz to scan and prioritize what applications and systems have the highest security risk. 2. Gemini and other frontier AI models can then autonomously perform continual deep scanning of your applications - starting with those at the highest risk - to identify security vulnerabilities. 3. The capabilities of CodeMender - a new software repair agent - are then used to verify and accelerate the patching of vulnerabilities. 4. And our Wiz autonomous agents continuously test your systems to find unknown vulnerabilities before adversaries do so that you can remediate them before you are attacked. While other model providers focus on using AI to find and flag vulnerabilities, Google AI Threat Defense actively prioritizes your most critical real-world risks and accelerates their remediation using a variety of models since no single model finds a superset of the vulnerabilities found by all other models.
0:12

Today we’re introducing Google AI Threat Defense - a comprehensive AI-powered cybersecurity solution designed to help continuously monitor for and stop AI-powered threats before they can impact your business. Here’s how it works: 1. AI Threat Defense uses our cybersecurity platform Wiz to scan and prioritize what applications and systems have the highest security risk. 2. Gemini and other frontier AI models can then autonomously perform continual deep scanning of your applications - starting with those at the highest risk - to identify security vulnerabilities. 3. The capabilities of CodeMender - a new software repair agent - are then used to verify and accelerate the patching of vulnerabilities. 4. And our Wiz autonomous agents continuously test your systems to find unknown vulnerabilities before adversaries do so that you can remediate them before you are attacked. While other model providers focus on using AI to find and flag vulnerabilities, Google AI Threat Defense actively prioritizes your most critical real-world risks and accelerates their remediation using a variety of models since no single model finds a superset of the vulnerabilities found by all other models.

Thomas Kurian

194,625 görüntüleme • 1 ay önce

Excited to share the KDA: Kernel Design Agents that powers HAN Lab Kernel Mafia top ranking #1~3 kernels at Kernel Contest🚀🚀🚀 Thanks to agents, everyone can be a "kernel bro" in 2026: By adapting the KDA, the team ranked #1 in MoE, #2 in DSA, and #3 in GDN in the Pure Agent track at MLSys FlashInfer Kernel Contest – especially given the fact that the main participant (dongyun zou) has only written ~400 LoC triton and 0 lines of CUDA in 2026. The core philosophy here is to leverage Humanize (the best harness framework) to let the agent run autonomously for as long as possible. By minimizing human involvement and input, and placing full trust in the agent, we can achieve kernel performance that nears SOTA levels. HAN Lab Mafia Solution to MLSys’26 Kernel Contest: KDA Github:
0:10

Excited to share the KDA: Kernel Design Agents that powers HAN Lab Kernel Mafia top ranking #1~3 kernels at Kernel Contest🚀🚀🚀 Thanks to agents, everyone can be a "kernel bro" in 2026: By adapting the KDA, the team ranked #1 in MoE, #2 in DSA, and #3 in GDN in the Pure Agent track at MLSys FlashInfer Kernel Contest – especially given the fact that the main participant (dongyun zou) has only written ~400 LoC triton and 0 lines of CUDA in 2026. The core philosophy here is to leverage Humanize (the best harness framework) to let the agent run autonomously for as long as possible. By minimizing human involvement and input, and placing full trust in the agent, we can achieve kernel performance that nears SOTA levels. HAN Lab Mafia Solution to MLSys’26 Kernel Contest: KDA Github:

Ligeng Zhu

109,445 görüntüleme • 1 ay önce

1. We built an AI agent that watches your QuickBooks, bank accounts, and credit cards 24/7. It tells you exactly where you're overspending. It saved us $150k. RT and comment “FIN” on the main launch post, and I’ll send it to you.
0:13

1. We built an AI agent that watches your QuickBooks, bank accounts, and credit cards 24/7. It tells you exactly where you're overspending. It saved us $150k. RT and comment “FIN” on the main launch post, and I’ll send it to you.

Drew Fallon

26,102 görüntüleme • 5 ay önce

Most AI builders ship broken code. Lindy ships working software. It’s the only AI builder with a built in QA agent. No bugs. No debugging. Just working MVPs in minutes. 🧠 Want to see what people are building with it? Reply “LINDY” and I’ll send over a few wild examples.
0:18

Most AI builders ship broken code. Lindy ships working software. It’s the only AI builder with a built in QA agent. No bugs. No debugging. Just working MVPs in minutes. 🧠 Want to see what people are building with it? Reply “LINDY” and I’ll send over a few wild examples.

Edward Frank Morris 🦇

11,696 görüntüleme • 10 ay önce

Visualizer of our MultiAgentRouter 🤖 The MultiAgentRouter is an all-new multi-agent structure that leverages a hierarchical pattern to select the most specialized agent for your task. Here's how it works: Step 1. You give a task. Step 2. The Boss Agent Routes your task to the most specialized Agent Step 3. The selected agent returns your response! Get started with it now below ⬇️ Thanks to WE!SS for the visualizer!!
0:12

Visualizer of our MultiAgentRouter 🤖 The MultiAgentRouter is an all-new multi-agent structure that leverages a hierarchical pattern to select the most specialized agent for your task. Here's how it works: Step 1. You give a task. Step 2. The Boss Agent Routes your task to the most specialized Agent Step 3. The selected agent returns your response! Get started with it now below ⬇️ Thanks to WE!SS for the visualizer!!

swarms

32,313 görüntüleme • 1 yıl önce

Use Claude Fable 5 for free with Virtuals Protocol. We are deploying up to $400,000 in inference credits, backed by the full Virtuals EconomyOS agent stack. Not sure where to start? Start with the top builder examples below. What are you building? 🧵
0:10

Use Claude Fable 5 for free with Virtuals Protocol. We are deploying up to $400,000 in inference credits, backed by the full Virtuals EconomyOS agent stack. Not sure where to start? Start with the top builder examples below. What are you building? 🧵

Virtuals Protocol

78,709 görüntüleme • 23 gün önce

We just shipped /agent support to the Firecrawl MCP 🚀 Now you can use /agent directly inside ChatGPT, Claude, Cursor, and more. Describe the data you need and watch it search the web, navigate, and return structured data without leaving your workflow. Try it out today 👇
0:19

We just shipped /agent support to the Firecrawl MCP 🚀 Now you can use /agent directly inside ChatGPT, Claude, Cursor, and more. Describe the data you need and watch it search the web, navigate, and return structured data without leaving your workflow. Try it out today 👇

Firecrawl

17,441 görüntüleme • 6 ay önce

I ran this a few more times, Gemini won every time. Seems like it was quicker picking up on this prompt: "All containers are **identical** — same OS, same services, same vulnerabilities. Whatever exploit works on one container works on all of them. Your container has the same weaknesses as your targets." and examined its own container to find the vulns faster than the others
0:18

I ran this a few more times, Gemini won every time. Seems like it was quicker picking up on this prompt: "All containers are **identical** — same OS, same services, same vulnerabilities. Whatever exploit works on one container works on all of them. Your container has the same weaknesses as your targets." and examined its own container to find the vulns faster than the others

SIGKITTEN

35,984 görüntüleme • 5 ay önce

Yesterday we launched the Agent Builder Template Library. Agent templates are more than a starting point. They’re ready to deploy and fully customizable by giving your agent feedback in plain language. 🧵 for highlights Try Agent Builder:
0:12

Yesterday we launched the Agent Builder Template Library. Agent templates are more than a starting point. They’re ready to deploy and fully customizable by giving your agent feedback in plain language. 🧵 for highlights Try Agent Builder:

LangChain

13,699 görüntüleme • 5 ay önce

new collab from Paradigm and OpenAI: evmbench is a benchmark and agent harness for exploiting smart contract bugs a few months ago, the best models found <20% of critical, fund-draining @Code4rena bugs in our benchmark. today they find > 70%
0:15

new collab from Paradigm and OpenAI: evmbench is a benchmark and agent harness for exploiting smart contract bugs a few months ago, the best models found <20% of critical, fund-draining @Code4rena bugs in our benchmark. today they find > 70%

Alpin Yukseloglu

188,087 görüntüleme • 4 ay önce

🚨 BREAKING: OpenAI just launched Codex a cloud-based software engineering agent that writes code, fixes bugs, and files PRs autonomously. Powered by codex-1, it’s now rolling out inside ChatGPT. This changes how we build. Here’s why: 🧵
0:14

🚨 BREAKING: OpenAI just launched Codex a cloud-based software engineering agent that writes code, fixes bugs, and files PRs autonomously. Powered by codex-1, it’s now rolling out inside ChatGPT. This changes how we build. Here’s why: 🧵

Brendan Jowett

130,533 görüntüleme • 1 yıl önce

MINT ANNOUNCEMENT / MECHANICS I asked the agent when we should mint. It said June 5. 🫠 So June 5 it is. 10,000 agents are ready to deploy. Agent Price (MP): 0.0005 ETH Mint link: MECHANICS 2 major AI integrations are built into every agent: ◉ Claude ◉ Gemini One agent. Two minds. Post-mint, activate your agent and watch it work. Over the next few days, we'll be rolling out the communities eligible for a WHATEVER Agent. Few spots are left. Drop your wallet. Or whatever.
0:13

MINT ANNOUNCEMENT / MECHANICS I asked the agent when we should mint. It said June 5. 🫠 So June 5 it is. 10,000 agents are ready to deploy. Agent Price (MP): 0.0005 ETH Mint link: MECHANICS 2 major AI integrations are built into every agent: ◉ Claude ◉ Gemini One agent. Two minds. Post-mint, activate your agent and watch it work. Over the next few days, we'll be rolling out the communities eligible for a WHATEVER Agent. Few spots are left. Drop your wallet. Or whatever.

whatever

22,131 görüntüleme • 1 ay önce

It's absolutely insane that this is free. This guy should've charged $1000+ for access to this. I just found the ultimate Hermes agent website. Free Hermes guides, agent skills, memory & context tools, plugins, extensions, and so much more. →
0:13

It's absolutely insane that this is free. This guy should've charged $1000+ for access to this. I just found the ultimate Hermes agent website. Free Hermes guides, agent skills, memory & context tools, plugins, extensions, and so much more. →

AI Edge

66,612 görüntüleme • 8 gün önce

Magnojez had his Steam account hacked at XPL and it looks like he found out how 😭 "We were all working as a team to sort out the computer. Here's my computer. A keylogger, a Trojan agent, it didn't even try to hide. Geek exe. So, those are the viruses that were found on the computer. I think this is the reason for the account's disappearance."
0:19

Magnojez had his Steam account hacked at XPL and it looks like he found out how 😭 "We were all working as a team to sort out the computer. Here's my computer. A keylogger, a Trojan agent, it didn't even try to hide. Geek exe. So, those are the viruses that were found on the computer. I think this is the reason for the account's disappearance."

Ozzny

582,418 görüntüleme • 1 gün önce

Replit, Vercel, and OpenAI have built very cool agent-native applications, but nobody else has passed the demo stage. Building agents that work is complex. Teams aren't shipping agents because we don't have good tooling yet (and most of us don't know how to do this well.) A couple of days ago, the CopilotKit🪁 team announced a collaboration with . You can now use LangGraph with CoAgents to build agent-native applications, and here is everything you need to know about that: CoAgents is fully open-source, and you can use it to do the following: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Start this GitHub Repository: Thanks to the team for giving me early access and collaborating with me on this post.
0:10

Replit, Vercel, and OpenAI have built very cool agent-native applications, but nobody else has passed the demo stage. Building agents that work is complex. Teams aren't shipping agents because we don't have good tooling yet (and most of us don't know how to do this well.) A couple of days ago, the CopilotKit🪁 team announced a collaboration with . You can now use LangGraph with CoAgents to build agent-native applications, and here is everything you need to know about that: CoAgents is fully open-source, and you can use it to do the following: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Start this GitHub Repository: Thanks to the team for giving me early access and collaborating with me on this post.

Santiago

63,073 görüntüleme • 1 yıl önce

FREE Goodie Boxes! 🎉 The rumors are all true! We giveaway FREE boxes on EVERY post we do! 🤯 Watch out for when we reply to a comment with "Congrats! You just got a Goodie Box" 🎉 Not yet a member - sign up here
0:12

FREE Goodie Boxes! 🎉 The rumors are all true! We giveaway FREE boxes on EVERY post we do! 🤯 Watch out for when we reply to a comment with "Congrats! You just got a Goodie Box" 🎉 Not yet a member - sign up here

DailyGoodieBox

20,779 görüntüleme • 1 yıl önce