Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Wake Arena: multi-agent AI audit with graph-driven reasoning and LLM-tailored static analysis. 43/94 high-severity vulnerabilities found in historical audit competitions. 26 findings, including 5 criticals in 4 production audits by Akcee in Nov 2025. Full benchmarking report: Built by senior auditors securing Lido, Aave, Axelar, and Safe. 50%+ true...

AckeeBlockchain's profile picture

Ackee Blockchain Security

9,465 subscribers

1,997,525 görüntüleme • 7 ay önce •via X (Twitter)

EğitimBilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

EVMbench for Solana: Trident Arena, a multi-agent AI security scanning solution. 21 out of 30 critical/high-severity vulnerabilities found across 6 open source Solana code bases in benchmarks. 70%+ true positive rate. See it in action: During a manual audit, TridentArena helped us find a critical-severity issue (later fixed), making MetaDAO even more secure. Built by the School of Solana senior auditors, securing leading protocols. Time to IBRL of Solana security audits! Launch blog post: Request access → Follow Trident for product updates and insights.
2:08

EVMbench for Solana: Trident Arena, a multi-agent AI security scanning solution. 21 out of 30 critical/high-severity vulnerabilities found across 6 open source Solana code bases in benchmarks. 70%+ true positive rate. See it in action: During a manual audit, TridentArena helped us find a critical-severity issue (later fixed), making MetaDAO even more secure. Built by the School of Solana senior auditors, securing leading protocols. Time to IBRL of Solana security audits! Launch blog post: Request access → Follow Trident for product updates and insights.

Ackee Blockchain Security

1,838,331 görüntüleme • 4 ay önce

Multimodal reasoning with Phi-4-reasoning-vision, new work on scaling LLM inference, benchmarking AI agents in network operations, cinematic video generation, adaptive evaluation for LLMs, and using AI to improve individual and population health.
2:00

Multimodal reasoning with Phi-4-reasoning-vision, new work on scaling LLM inference, benchmarking AI agents in network operations, cinematic video generation, adaptive evaluation for LLMs, and using AI to improve individual and population health.

Microsoft Research

11,672 görüntüleme • 4 ay önce

Mythos Preview has already found thousands of high-severity vulnerabilities—including some in every major operating system and web browser.
5:48

Mythos Preview has already found thousands of high-severity vulnerabilities—including some in every major operating system and web browser.

Anthropic

2,038,566 görüntüleme • 3 ay önce

🚨 New Feature in OctoMCP: AI Audits Are Live! OctoMCP now supports AI-powered audits for Generated Solana programs! Use the generate-AI-Audit tool to perform automated audits using the LLM configured in your MCP host. 🔍 What it does: Supports 3 audit types: basic, comprehensive, and security-focused Analyzes your program’s source code and IDL Detects critical, high, medium, low, and informational issues Reports code metrics like lines of code, functions, complexity, and nesting depth Provides security best practices and actionable recommendations Includes program context like name, instructions, accounts, and types Generates a clean, structured Markdown audit report 🚧 What’s coming next: We’re working on major updates including: AI Fuzzer Functions using open-source Solana fuzzing frameworks AI Testing Kit to auto-generate test files and validate your programs Octobuild – Build everything right in the browser, 3× faster than OctoMCP, no MCP setup required 🚀 Start vibe coding Solana Dapps + programs today! Deployed Piggybank Program:
2:49

🚨 New Feature in OctoMCP: AI Audits Are Live! OctoMCP now supports AI-powered audits for Generated Solana programs! Use the generate-AI-Audit tool to perform automated audits using the LLM configured in your MCP host. 🔍 What it does: Supports 3 audit types: basic, comprehensive, and security-focused Analyzes your program’s source code and IDL Detects critical, high, medium, low, and informational issues Reports code metrics like lines of code, functions, complexity, and nesting depth Provides security best practices and actionable recommendations Includes program context like name, instructions, accounts, and types Generates a clean, structured Markdown audit report 🚧 What’s coming next: We’re working on major updates including: AI Fuzzer Functions using open-source Solana fuzzing frameworks AI Testing Kit to auto-generate test files and validate your programs Octobuild – Build everything right in the browser, 3× faster than OctoMCP, no MCP setup required 🚀 Start vibe coding Solana Dapps + programs today! Deployed Piggybank Program:

OctonetAI

30,888 görüntüleme • 1 yıl önce

audit and fix your entire developer docs site in under a minute We built an AI agent with Browserbase and Cerebras that audits your entire docs site > point it at any documentation site > agent goes down the link tree > agent crawls and verifies every page, checks every link, reads every code snippet > agent also compares content to your GitHub repo > returns a full report with suggested fixes and source references The full code and tutorial for how to build this yourself is live now.
1:16

audit and fix your entire developer docs site in under a minute We built an AI agent with Browserbase and Cerebras that audits your entire docs site > point it at any documentation site > agent goes down the link tree > agent crawls and verifies every page, checks every link, reads every code snippet > agent also compares content to your GitHub repo > returns a full report with suggested fixes and source references The full code and tutorial for how to build this yourself is live now.

Sarah Chieng

26,679 görüntüleme • 3 ay önce

Thank you to Boston 25 News and WCVB-TV Boston for the opportunity to highlight the serious findings in our recent audit of Early Education and Care. To read the full audit report, visit #mapoli
0:54

Thank you to Boston 25 News and WCVB-TV Boston for the opportunity to highlight the serious findings in our recent audit of Early Education and Care. To read the full audit report, visit #mapoli

Diana DiZoglio

16,586 görüntüleme • 1 yıl önce

Holy shit...Google just dropped CodeMender an autonomous AI agent that finds and fixes security bugs in code by itself. This isn’t a static analysis tool. It’s a self-reasoning system that patches vulnerabilities and rewrites insecure code before humans even find it. Let’s break it down ↓
0:42

Holy shit...Google just dropped CodeMender an autonomous AI agent that finds and fixes security bugs in code by itself. This isn’t a static analysis tool. It’s a self-reasoning system that patches vulnerabilities and rewrites insecure code before humans even find it. Let’s break it down ↓

Hasan Toor

127,108 görüntüleme • 7 ay önce

Introducing CRABWISE 🦀 Build trust with your agents and set rules they can't break. Local-first agent monitoring, audit trail, and policy enforcement with multi-agent, multi-provider support → live agent monitoring → local policy enforcement (commandments) → a hash-chained audit trail → terminal UIs for status, watch, and audit → support for OpenClaw, Claude Code, Codex CLI (more to come) + pairs nicely with Crabwalk🦀 Follow me Luciano Castillo to stay updated + RT!
0:21

Introducing CRABWISE 🦀 Build trust with your agents and set rules they can't break. Local-first agent monitoring, audit trail, and policy enforcement with multi-agent, multi-provider support → live agent monitoring → local policy enforcement (commandments) → a hash-chained audit trail → terminal UIs for status, watch, and audit → support for OpenClaw, Claude Code, Codex CLI (more to come) + pairs nicely with Crabwalk🦀 Follow me Luciano Castillo to stay updated + RT!

Luciano Castillo

13,929 görüntüleme • 4 ay önce

Your agent, your instance, your choice of model, crypto enabled, and a secure agent app store for you to add skills, strategies, automations and more… Wayfinder also has a shared user/agent interface for hyperliquid and polymarket. Plus, agent access to Boros, aave, Euler, pendle, aerodrome, uniswap, and many more protocols through the Wayfinder sdk. Wayfinder Foundation 🧭 contracts are in audit and release is planned post completion with $PROMPT as collateral for publishing and securing paths.
1:13

Your agent, your instance, your choice of model, crypto enabled, and a secure agent app store for you to add skills, strategies, automations and more… Wayfinder also has a shared user/agent interface for hyperliquid and polymarket. Plus, agent access to Boros, aave, Euler, pendle, aerodrome, uniswap, and many more protocols through the Wayfinder sdk. Wayfinder Foundation 🧭 contracts are in audit and release is planned post completion with $PROMPT as collateral for publishing and securing paths.

//Kalos

199,019 görüntüleme • 2 ay önce

Multimodal Reasoning AI Agents are here with Gemini 2.0 Flash Thinking I built a multimodal AI agent that can reason and understand images using gemini flash reasoning LLM. 100% Opensource Code with step-by-step tutorial.
0:20

Multimodal Reasoning AI Agents are here with Gemini 2.0 Flash Thinking I built a multimodal AI agent that can reason and understand images using gemini flash reasoning LLM. 100% Opensource Code with step-by-step tutorial.

Shubham Saboo

36,596 görüntüleme • 1 yıl önce

Meet Replit Security Agent - providing comprehensive app security reviews in minutes And you get $5 in credits to try it for a limited time Security Agent’s hybrid static analysis and AI-scanning approach is first of its kind: - Acts on custom threat model to review full codebase - Resolves vulnerabilities in parallel using background tasks - Reduces false positives by 90% Powered by Semgrep + @HoundDogAI. Keep vibe coding safely 🔒
0:25

Meet Replit Security Agent - providing comprehensive app security reviews in minutes And you get $5 in credits to try it for a limited time Security Agent’s hybrid static analysis and AI-scanning approach is first of its kind: - Acts on custom threat model to review full codebase - Resolves vulnerabilities in parallel using background tasks - Reduces false positives by 90% Powered by Semgrep + @HoundDogAI. Keep vibe coding safely 🔒

Replit ⠕

86,083 görüntüleme • 2 ay önce

Errors Identified in Fulton County Audit Report An analysis by the Rossie James team identified 36 factual errors in the Fulton County hand audit report published by the Secretary of State. These errors represented over 4,000 false absentee ballot votes out of 147,000 counted, a 2.7% error rate. The errors were validated by Governor Kemp's team. Admissions of Flawed Audit Report Initially the Secretary of State's office denied errors, but after the Governor's validation they admitted the Fulton County audit report was severely flawed. In a radio interview the Secretary of State acknowledged "they were off by several thousand ballots" because some ballots were scanned twice. Damage to Election Integrity Mr. Watters argues the audit errors and flawed report from Fulton County does not inspire confidence or trust in the election results. He says it was sloppy, inconsistent, and undermines election integrity.
2:18

Errors Identified in Fulton County Audit Report An analysis by the Rossie James team identified 36 factual errors in the Fulton County hand audit report published by the Secretary of State. These errors represented over 4,000 false absentee ballot votes out of 147,000 counted, a 2.7% error rate. The errors were validated by Governor Kemp's team. Admissions of Flawed Audit Report Initially the Secretary of State's office denied errors, but after the Governor's validation they admitted the Fulton County audit report was severely flawed. In a radio interview the Secretary of State acknowledged "they were off by several thousand ballots" because some ballots were scanned twice. Damage to Election Integrity Mr. Watters argues the audit errors and flawed report from Fulton County does not inspire confidence or trust in the election results. He says it was sloppy, inconsistent, and undermines election integrity.

White 🤍 Queen

29,451 görüntüleme • 2 yıl önce

Google Gemini just dropped 4 updates 🤯 AI music, AI product photos, smarter reasoning, and AI-built presentations are all here. Want the full guide? DM me.
1:13

Google Gemini just dropped 4 updates 🤯 AI music, AI product photos, smarter reasoning, and AI-built presentations are all here. Want the full guide? DM me.

Julian Goldie SEO

12,116 görüntüleme • 4 ay önce

Allen Iverson would stay out until 4 in the morning and then wake up and drop 50 the next day. AI was built different 😳
1:00

Allen Iverson would stay out until 4 in the morning and then wake up and drop 50 the next day. AI was built different 😳

NBACentral

1,012,167 görüntüleme • 8 ay önce

Gemini 3.5 flash + Gemini managed agents api just audited a real megatron-lm ci failure inside Eigent. root cause in minutes! watch the handoff: coordinator agent plans the audit, developer agent loads the ml-failure-audit skill and gathers the evidence, then gemini agent steps in as a remote sub-agent for the heavy reasoning. gemini managed agents api and gemini 3.5 flash now live on our open-source cowork Eigent! Google AI Developers Google AI Studio
1:30

Gemini 3.5 flash + Gemini managed agents api just audited a real megatron-lm ci failure inside Eigent. root cause in minutes! watch the handoff: coordinator agent plans the audit, developer agent loads the ml-failure-audit skill and gathers the evidence, then gemini agent steps in as a remote sub-agent for the heavy reasoning. gemini managed agents api and gemini 3.5 flash now live on our open-source cowork Eigent! Google AI Developers Google AI Studio

Eigent AI

16,335 görüntüleme • 1 ay önce

Wild. Nate Herkelman built an AI agent in n8n.io that auto-selects the best LLM for any task... and logs why! 🤯 Full demo in 🧵↓
2:33

Wild. Nate Herkelman built an AI agent in n8n.io that auto-selects the best LLM for any task... and logs why! 🤯 Full demo in 🧵↓

Charly Wargnier

130,761 görüntüleme • 1 yıl önce

1/n: 🤖 I just built a production-ready crypto Telegram bot in ONE day with Claude + MCP integration. AI coder agents are already a reality and if you're not leveraging MCP servers right now you're missing out on some serious productivity gains. Get a local AI agent in 5 minutes with Anthropic's new open-source server protocol for LLM connections. 🧶
0:22

1/n: 🤖 I just built a production-ready crypto Telegram bot in ONE day with Claude + MCP integration. AI coder agents are already a reality and if you're not leveraging MCP servers right now you're missing out on some serious productivity gains. Get a local AI agent in 5 minutes with Anthropic's new open-source server protocol for LLM connections. 🧶

kaue

10,596 görüntüleme • 1 yıl önce

Introducing: Immunefi Audits 🛡️ Powered by web3’s very best security researchers, each proven by the most demanding trial: to save protocols from real funds-at-risk mainnet vulnerabilities. No auditors are so elite, nor so proven. You get the best audit, every time.
0:35

Introducing: Immunefi Audits 🛡️ Powered by web3’s very best security researchers, each proven by the most demanding trial: to save protocols from real funds-at-risk mainnet vulnerabilities. No auditors are so elite, nor so proven. You get the best audit, every time.

Immunefi

812,626 görüntüleme • 1 yıl önce