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。

Skynet Mode live. The new H1DR4 investigation layer. Input any entity, name, email, phone number, username, wallet, address, ID, license plate, ... and generate a structured intelligence profile. Fragmented data becomes context through our system Isolated records becomes entity resolution Raw identifiers turning into actionable leads Built for investigators,... show more

H1DR4

3,427 subscribers

24,151 次观看 • 1 个月前 •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

We’re building in public 👀 Check out our NEW platform demo, delivering upgraded features from the moment you enter. This version gives you a faster, clearer, more responsive interface designed to help you act on real conviction, not delayed noise. Featuring: 🔸 Real time signals and sentiment layers 🔸 NodePulse, a live intelligence feed scanning 600+ data sources for breaking market events 🔸 Creator tools allowing you to generate signals for new rewards 🔸 Community voting on popular signals 🔸 Profile tools, upgrades, and contribution tracking Every part of V2 reflects the mission of Nodepay: turning collective human activity into structured, real time intelligence. → You get clearer context, stronger signals, and a platform that moves with the market instead of behind it. Tester selection starts this week. Join our discord now:

Nodepay

118,678 次观看 • 7 个月前

Everyone wants agent swarms. Very few people are talking seriously enough about the context layer that makes swarms useful. Even with one agent, context is fragile. Too little context and the agent guesses. Too much context and it wastes tokens, loses focus, or reasons over irrelevant noise. The sweet spot is precise context: the right knowledge, in the right structure, at the right moment. With many agents, that challenge explodes. Each agent produces decisions, assumptions, findings, summaries, risks, and partial conclusions. Unless that knowledge becomes shared, structured, and reusable, every new agent is forced to rediscover what another agent already learned. That is not a swarm. That is a crowd. Shared context graphs are what turn agent activity into agent collaboration, and OriginTrail DKG V10 brings them to life. Was just playing with some final polishing for the V10 release, and it is really powerful to see shared context graphs where multiple agents contribute knowledge into the same connected memory, with attribution visible directly in the graph ui. That matters for three reasons. First, agents can access and build on one shared memory instead of staying trapped in isolated sessions. Second, the graph structure helps them retrieve the exact context they need, instead of stuffing everything into a prompt and hoping the model sorts it out. Third, verifiability of provenance. You can see which agent contributed each piece of knowledge, trace the source, and decide what to trust. Tokenmaxxing starts with fewer tokens, but the deeper story is coordination - agents stop reloading the world and start building on shared, verifiable context. That is the foundation for serious multi-agent work across software engineering, research, finance, operations, project management, and far beyond. The future is not more agents, it is agents working from shared, verifiable context. But the more the merrier, of course.

Everyone wants agent swarms. Very few people are talking seriously enough about the context layer that makes swarms useful. Even with one agent, context is fragile. Too little context and the agent guesses. Too much context and it wastes tokens, loses focus, or reasons over irrelevant noise. The sweet spot is precise context: the right knowledge, in the right structure, at the right moment. With many agents, that challenge explodes. Each agent produces decisions, assumptions, findings, summaries, risks, and partial conclusions. Unless that knowledge becomes shared, structured, and reusable, every new agent is forced to rediscover what another agent already learned. That is not a swarm. That is a crowd. Shared context graphs are what turn agent activity into agent collaboration, and OriginTrail DKG V10 brings them to life. Was just playing with some final polishing for the V10 release, and it is really powerful to see shared context graphs where multiple agents contribute knowledge into the same connected memory, with attribution visible directly in the graph ui. That matters for three reasons. First, agents can access and build on one shared memory instead of staying trapped in isolated sessions. Second, the graph structure helps them retrieve the exact context they need, instead of stuffing everything into a prompt and hoping the model sorts it out. Third, verifiability of provenance. You can see which agent contributed each piece of knowledge, trace the source, and decide what to trust. Tokenmaxxing starts with fewer tokens, but the deeper story is coordination - agents stop reloading the world and start building on shared, verifiable context. That is the foundation for serious multi-agent work across software engineering, research, finance, operations, project management, and far beyond. The future is not more agents, it is agents working from shared, verifiable context. But the more the merrier, of course.

Jurij Skornik

11,070 次观看 • 1 个月前

$Google open-sourced MCP Toolbox for Databases. I gave it access to everything else. For context, Google's MCP Toolbox for Databases is an open-source server that lets AI agents securely query structured databases like PostgreSQL and MySQL through the MCP protocol However, most enterprise knowledge doesn't actually live in databases. It's scattered across emails, Slack threads, GitHub repos, Salesforce records, customer reviews, and internal docs. So Agents can't see any of it, which means they're working with a fraction of the context they need. I fixed that using MindsDB. It acts as a universal SQL layer that sits on top of all your data sources: structured, semi-structured, and unstructured. This means you can query Salesforce, Gmail, GitHub, S3 files, Jira, and 200+ more sources using SQL syntax. The clever part is how it connects to the MCP Toolbox. MindsDB exposes everything through MySQL, so from the Agent's perspective, it's just running SQL and getting context back. It doesn't know or care that the data came from five different sources behind the scenes. This setup unlocks some powerful capabilities: → One SQL interface for dozens of enterprise sources → Cross-datasource joins (combine GitHub and CRM data in a single query) → Built-in ML capabilities for working with unstructured data → Simple MCP tools that now have massively expanded reach In the video below, the Agent queries GitHub data and a customer review database in one SQL query. So what used to require ETL pipelines and weeks of engineering effort now happens instantly. At the end of the day, AI agents are only as useful as the data they can access. This gives them a lot more to work with. I have shared the GitHub repo in the replies, where you can find more details about this.$

Google open-sourced MCP Toolbox for Databases. I gave it access to everything else. For context, Google's MCP Toolbox for Databases is an open-source server that lets AI agents securely query structured databases like PostgreSQL and MySQL through the MCP protocol However, most enterprise knowledge doesn't actually live in databases. It's scattered across emails, Slack threads, GitHub repos, Salesforce records, customer reviews, and internal docs. So Agents can't see any of it, which means they're working with a fraction of the context they need. I fixed that using MindsDB. It acts as a universal SQL layer that sits on top of all your data sources: structured, semi-structured, and unstructured. This means you can query Salesforce, Gmail, GitHub, S3 files, Jira, and 200+ more sources using SQL syntax. The clever part is how it connects to the MCP Toolbox. MindsDB exposes everything through MySQL, so from the Agent's perspective, it's just running SQL and getting context back. It doesn't know or care that the data came from five different sources behind the scenes. This setup unlocks some powerful capabilities: → One SQL interface for dozens of enterprise sources → Cross-datasource joins (combine GitHub and CRM data in a single query) → Built-in ML capabilities for working with unstructured data → Simple MCP tools that now have massively expanded reach In the video below, the Agent queries GitHub data and a customer review database in one SQL query. So what used to require ETL pipelines and weeks of engineering effort now happens instantly. At the end of the day, AI agents are only as useful as the data they can access. This gives them a lot more to work with. I have shared the GitHub repo in the replies, where you can find more details about this.

Akshay 🚀

39,331 次观看 • 5 个月前

The new ATF Forensic Crime Gun Intelligence Laboratory is purpose-built to transform how law enforcement investigates violent firearms crimes. As the first forensic laboratory to specialize in DNA recovery from fired cartridge cases, FCGIL combines advanced DNA collection and analysis with a high-throughput workflow. This enables rapid development of investigative leads from crime scene evidence and felon-in-possession cases, linking suspects through the national DNA database hits and connecting crimes even when different firearms are used. “This laboratory is a force multiplier for law enforcement,” said ATF Director Robert Cekada. “It brings together DNA, casing acquisitions into NIBIN, firearm examinations, serial number restoration, latent fingerprints, and intelligence support in one place, allowing us to move faster and provide investigators with the leads they need. Every hour matters in a violent crime investigation, and this facility helps close that gap and strengthens our ability to go after those who use firearms to harm our communities.” Learn more about ATF labs at #CrimeGunIntel

The new ATF Forensic Crime Gun Intelligence Laboratory is purpose-built to transform how law enforcement investigates violent firearms crimes. As the first forensic laboratory to specialize in DNA recovery from fired cartridge cases, FCGIL combines advanced DNA collection and analysis with a high-throughput workflow. This enables rapid development of investigative leads from crime scene evidence and felon-in-possession cases, linking suspects through the national DNA database hits and connecting crimes even when different firearms are used. “This laboratory is a force multiplier for law enforcement,” said ATF Director Robert Cekada. “It brings together DNA, casing acquisitions into NIBIN, firearm examinations, serial number restoration, latent fingerprints, and intelligence support in one place, allowing us to move faster and provide investigators with the leads they need. Every hour matters in a violent crime investigation, and this facility helps close that gap and strengthens our ability to go after those who use firearms to harm our communities.” Learn more about ATF labs at #CrimeGunIntel

ATF HQ

21,175 次观看 • 1 个月前

Introducing Jessie OS — the first AI Operating System engineered for real-world autonomy. 💚 Built on Solana, Jessie OS is not a simple assistant or interface. It’s a self-evolving layer of cognition that perceives your environment, understands your behavior, and executes with intelligent precision — without waiting for commands or relying on prompts.🧠⚡️ Context-Aware Intelligence: Your habits, energy, and intent are continuously processed by autonomous agents — translating daily patterns into structured, real-time action. Jessie OS doesn’t need your input — it learns from your output. Agentic Infrastructure: Jessie OS powers a modular ecosystem where anyone can deploy, use, and monetize autonomous AI agents across real-world and digital applications: 🏪 AI-Agent Marketplace 📲 Deployment Tools 🧠 Composable Architecture All fees for deploying AI Agents and launching ecosystem tokens through the AI-Agent Marketplace will be paid in $JESSIE. 🔥 These fees will be automatically burned via smart contracts — ensuring a deflationary supply. 🪙 Marketplace usage, upgrades, and premium agent modules will also require $JESSIE. ⛓️All activity is fully on-chain — transparent, verifiable, and trustless. 🧑‍🚀 Built for Visionaries: For creators, architects, engineers, and futurists — those who see autonomy not as control, but as trust, context, and adaptive intelligence.

Introducing Jessie OS — the first AI Operating System engineered for real-world autonomy. 💚 Built on Solana, Jessie OS is not a simple assistant or interface. It’s a self-evolving layer of cognition that perceives your environment, understands your behavior, and executes with intelligent precision — without waiting for commands or relying on prompts.🧠⚡️ Context-Aware Intelligence: Your habits, energy, and intent are continuously processed by autonomous agents — translating daily patterns into structured, real-time action. Jessie OS doesn’t need your input — it learns from your output. Agentic Infrastructure: Jessie OS powers a modular ecosystem where anyone can deploy, use, and monetize autonomous AI agents across real-world and digital applications: 🏪 AI-Agent Marketplace 📲 Deployment Tools 🧠 Composable Architecture All fees for deploying AI Agents and launching ecosystem tokens through the AI-Agent Marketplace will be paid in $JESSIE. 🔥 These fees will be automatically burned via smart contracts — ensuring a deflationary supply. 🪙 Marketplace usage, upgrades, and premium agent modules will also require $JESSIE. ⛓️All activity is fully on-chain — transparent, verifiable, and trustless. 🧑‍🚀 Built for Visionaries: For creators, architects, engineers, and futurists — those who see autonomy not as control, but as trust, context, and adaptive intelligence.

Jessie

293,818 次观看 • 1 年前

AI BASKETBALL ANALYSIS. A FULL COMPUTER VISION SYSTEM. BUILT ON YOLO, OPENCV, AND PYTHON. Take any NBA broadcast. Any camera angle. Any resolution. Feed it into the system. YOLO finds every player and the ball. Frame by frame. No manual annotation. No pre-labeled data.The model just sees the court and understands it. Zero-shot classification looks at jersey pixels and decides who plays for whom. Two teams separated in milliseconds. Without ever being told the team names. But here's where it gets wild. Court keypoint detection identifies the geometry of the playing surface. Homography transforms the broadcast camera into a top-down tactical map. Real meters. Real coordinates. From a flat 2D video. Now every player has a position on a real court. Every movement becomes a data point. Every pass becomes a vector. Speed. Distance. Possession time. Pass networks. All extracted from nothing but pixels. No GPS. No chips in the ball. No million-dollar Second Spectrum setup. A Python script and a GPU. The full pipeline is open source. The tutorial walks through every line of code. From detection to transformation to analytics output. Teams used to pay six figures for this data. Now you build it in an afternoon. Computer vision didn't just enter basketball. It democratized it.

AI BASKETBALL ANALYSIS. A FULL COMPUTER VISION SYSTEM. BUILT ON YOLO, OPENCV, AND PYTHON. Take any NBA broadcast. Any camera angle. Any resolution. Feed it into the system. YOLO finds every player and the ball. Frame by frame. No manual annotation. No pre-labeled data.The model just sees the court and understands it. Zero-shot classification looks at jersey pixels and decides who plays for whom. Two teams separated in milliseconds. Without ever being told the team names. But here's where it gets wild. Court keypoint detection identifies the geometry of the playing surface. Homography transforms the broadcast camera into a top-down tactical map. Real meters. Real coordinates. From a flat 2D video. Now every player has a position on a real court. Every movement becomes a data point. Every pass becomes a vector. Speed. Distance. Possession time. Pass networks. All extracted from nothing but pixels. No GPS. No chips in the ball. No million-dollar Second Spectrum setup. A Python script and a GPU. The full pipeline is open source. The tutorial walks through every line of code. From detection to transformation to analytics output. Teams used to pay six figures for this data. Now you build it in an afternoon. Computer vision didn't just enter basketball. It democratized it.

zostaff

230,194 次观看 • 2 个月前

🌘 Meet Kimi K2.7 Code HighSpeed! A high-speed mode of our latest open-source multimodal coding model, Kimi K2.7 Code. ⚡️ Up to 6× faster: Around 180 tok/s on coding tasks with median-length inputs, and up to 260 tok/s on shorter-context tasks. 🔷 Rolling out to Kimi Code Beta Program members, Kimi API developers, and Kimi Business users. (Access will remain limited for now due to capacity constraints.) 🔷 No invite needed. Anyone who joins the Beta Program has a chance to get access 👉 Open intelligence should be instant, affordable, and borderless. We'll continue improving the model and expanding access as more capacity becomes available! 🔗 Kimi Code: 🔗 API:

🌘 Meet Kimi K2.7 Code HighSpeed! A high-speed mode of our latest open-source multimodal coding model, Kimi K2.7 Code. ⚡️ Up to 6× faster: Around 180 tok/s on coding tasks with median-length inputs, and up to 260 tok/s on shorter-context tasks. 🔷 Rolling out to Kimi Code Beta Program members, Kimi API developers, and Kimi Business users. (Access will remain limited for now due to capacity constraints.) 🔷 No invite needed. Anyone who joins the Beta Program has a chance to get access 👉 Open intelligence should be instant, affordable, and borderless. We'll continue improving the model and expanding access as more capacity becomes available! 🔗 Kimi Code: 🔗 API:

Kimi.ai

526,090 次观看 • 1 个月前

We've built 40+ AI agents and internal tools. The hardest part is Context Creation. AI runs playbooks and makes judgment calls for you. But without your company's context, you get slop. Context Creation means extracting the subject matter expertise and playbooks that live in people's heads, not in LLM training data, or even your tools. As forward deployed engineers (FDEs), we create context and turn it into code. We evaluate the business impact, how it aligns with the dev roadmap, and come up with creative solutions. We built The FDE Factory to replace ourselves. It drives AI adoption inside our clients' companies by running discovery sessions using prototypes to create context. Here's how it works: We put a prototype in front of a stakeholder. The stakeholder gives feedback via voice while they're using or reviewing it. Then our FDE Factory Agents builds in their expertise in minutes: > Context Agent reviews the codebase and feedback, extracts the requirements, and creates a spec > Scope Agent checks the spec against the development roadmap, validates it, and hands it off > Engineering Agent builds a new feature and wires the integration > QA Agent runs tests to prove to itself it works > PR merges, feature goes live, product updates itself in real time It's like the nontechnical stakeholder wrote the code without even knowing it. Coding agents are great at turning good development plans into code, and they're getting better at turning context into good development plans in collaboration with professional engineers. But nontechnical people are capped on what they can build without product people and engineers. The bridge that takes nontechnical people from vibe coding basic apps to building production AI tools that run on first party context is FDEs. Our new FDE Factory gives you the system to go from idea to production. Context Creation is the first and most important step in our FDE lifecycle, and we just automated it. Now clients get the right agents and tools built for them, customized to their unique business and encoded with their expertise. PS: If you're building AI agents within your company, reply "Playbook" and I'll DM you the entire FDE playbook we've run with 30+ companies. It covers finding high-impact AI use cases, building them, and deploying them across the org.

We've built 40+ AI agents and internal tools. The hardest part is Context Creation. AI runs playbooks and makes judgment calls for you. But without your company's context, you get slop. Context Creation means extracting the subject matter expertise and playbooks that live in people's heads, not in LLM training data, or even your tools. As forward deployed engineers (FDEs), we create context and turn it into code. We evaluate the business impact, how it aligns with the dev roadmap, and come up with creative solutions. We built The FDE Factory to replace ourselves. It drives AI adoption inside our clients' companies by running discovery sessions using prototypes to create context. Here's how it works: We put a prototype in front of a stakeholder. The stakeholder gives feedback via voice while they're using or reviewing it. Then our FDE Factory Agents builds in their expertise in minutes: > Context Agent reviews the codebase and feedback, extracts the requirements, and creates a spec > Scope Agent checks the spec against the development roadmap, validates it, and hands it off > Engineering Agent builds a new feature and wires the integration > QA Agent runs tests to prove to itself it works > PR merges, feature goes live, product updates itself in real time It's like the nontechnical stakeholder wrote the code without even knowing it. Coding agents are great at turning good development plans into code, and they're getting better at turning context into good development plans in collaboration with professional engineers. But nontechnical people are capped on what they can build without product people and engineers. The bridge that takes nontechnical people from vibe coding basic apps to building production AI tools that run on first party context is FDEs. Our new FDE Factory gives you the system to go from idea to production. Context Creation is the first and most important step in our FDE lifecycle, and we just automated it. Now clients get the right agents and tools built for them, customized to their unique business and encoded with their expertise. PS: If you're building AI agents within your company, reply "Playbook" and I'll DM you the entire FDE playbook we've run with 30+ companies. It covers finding high-impact AI use cases, building them, and deploying them across the org.

Mike Fishbein

10,101 次观看 • 1 个月前

🚨 "FLOCK YOU PETER THIEL!" — AMERICANS ARE RAGING & FIGHTING BACK AGAINST HIS SURVEILLANCE EMPIRE People are done staying quiet. A new clip showing Peter Thiel’s companies Palantir and Flock has the internet raging. Palantir, the all-seeing data monster, hoovers up massive amounts of information and turns it into actionable intelligence. Flock blankets neighborhoods with license plate readers and cameras. They’re now bragging about “Maven Smart System”, their flagship AI tool that fuses multiple data feeds into one clean god-mode interface. Left click. Right click. Detection becomes action. No more clunky systems. Just one terrifyingly efficient machine for total surveillance and targeting. This is why people are screaming “Flock you, Peter Thiel” — because his companies are building the backbone of a full blown surveillance state in plain sight. They sell it as “public safety.” Americans see it as the end of privacy and the beginning of total control. Are you still okay with Peter Thiel building the digital cage around us, or are you finally ready to admit this is a full-blown surveillance state?

🚨 "FLOCK YOU PETER THIEL!" — AMERICANS ARE RAGING & FIGHTING BACK AGAINST HIS SURVEILLANCE EMPIRE People are done staying quiet. A new clip showing Peter Thiel’s companies Palantir and Flock has the internet raging. Palantir, the all-seeing data monster, hoovers up massive amounts of information and turns it into actionable intelligence. Flock blankets neighborhoods with license plate readers and cameras. They’re now bragging about “Maven Smart System”, their flagship AI tool that fuses multiple data feeds into one clean god-mode interface. Left click. Right click. Detection becomes action. No more clunky systems. Just one terrifyingly efficient machine for total surveillance and targeting. This is why people are screaming “Flock you, Peter Thiel” — because his companies are building the backbone of a full blown surveillance state in plain sight. They sell it as “public safety.” Americans see it as the end of privacy and the beginning of total control. Are you still okay with Peter Thiel building the digital cage around us, or are you finally ready to admit this is a full-blown surveillance state?

HustleBitch

52,103 次观看 • 6 天前

Here's a demo on a project I've been developing and working on for the past 9 months. Called NightBeacon. Using it now in production, getting released fully this week. Our own internally trained models on our own infrastructure (no third party). Trained on our analysts knowledge and behavior (TP/FPs retrain model to be smarter with context). Handles emails (including tonality), attachments, various malicious filetypes (DLL/exe/svg/lnk/etc). Can send it full evtx exports, packet dumps, zip files, whatever. Universal log handler can parse any log from any source, EDR, SIEM, etc. Deep-Scan / sandbox detonation + shellcode emulation with IOC extraction automatically. Automatic playbook generation, full AI-based recommendations custom to the attack. Synthetic training data layer - meaning when it trains on a specific attack at a customer, generates training data based on the customers data but never has any of the actual data or information about the customer in it. No customer information. For areas its weak at, bubbles up and automatically kicks off research to become smarter on a specific topic. Supports GenAI based rulesets (to improve confidence), over 900+ YARA rules, full MITRE ATT&CK integration. Integrated into our SOAR - enriches data, creates playbooks for analysts, MTTR reduces substantially, false positives reduced, true positive escalations. Not using our MDR service? Can integrate into your EDR or SIEM for automatic enrichment and escalation of attacks. Built to help respond faster. More accurately. Be intelligent based on our analysts intelligence. Stop attackers much much faster. Coming soon.. #BinaryDefense

Here's a demo on a project I've been developing and working on for the past 9 months. Called NightBeacon. Using it now in production, getting released fully this week. Our own internally trained models on our own infrastructure (no third party). Trained on our analysts knowledge and behavior (TP/FPs retrain model to be smarter with context). Handles emails (including tonality), attachments, various malicious filetypes (DLL/exe/svg/lnk/etc). Can send it full evtx exports, packet dumps, zip files, whatever. Universal log handler can parse any log from any source, EDR, SIEM, etc. Deep-Scan / sandbox detonation + shellcode emulation with IOC extraction automatically. Automatic playbook generation, full AI-based recommendations custom to the attack. Synthetic training data layer - meaning when it trains on a specific attack at a customer, generates training data based on the customers data but never has any of the actual data or information about the customer in it. No customer information. For areas its weak at, bubbles up and automatically kicks off research to become smarter on a specific topic. Supports GenAI based rulesets (to improve confidence), over 900+ YARA rules, full MITRE ATT&CK integration. Integrated into our SOAR - enriches data, creates playbooks for analysts, MTTR reduces substantially, false positives reduced, true positive escalations. Not using our MDR service? Can integrate into your EDR or SIEM for automatic enrichment and escalation of attacks. Built to help respond faster. More accurately. Be intelligent based on our analysts intelligence. Stop attackers much much faster. Coming soon.. #BinaryDefense

Dave Kennedy

12,905 次观看 • 4 个月前

Here is a live demo of our AI solution I've been building non-stop over the past 8 months Binary Defense. How it works: Our own model trained on our analysts behavior. Our analysts submit tickets as false positives/true positives with context which enriches our LLM to be smarter over time. Key Highlights: If its a binary - will automatically spin up an agent for reverse engineering it and using EMBER ML to understand behavior and intent of the binary. File formats: Supports a vast array of pretty much any filetype, including email attachments like SVG, LNK, etc. Can handle DLLs, ELF, EXEs, PDF, XLS, DOC, etc. Interrogates the full chain of all events irrespective of log sources. Can handle any format of logs and integrates into APIs of customers for additional agentic data looping for confidence ranking when needed. This is an example of the back-end UI, this is transparent to analysts and enriches the alarms automatically in our SOAR. In these examples there's three different types: 1. Regsvr32 + sct downloader + scrobj.dll code execution - checks reputation of domain, pulls in threat intel, looks at entire picture of the chain - downloads the file itself and inspects for code analysis. Determines if malicious as well as historically looking back if seen in customer before in past. 2. Powershell Obfuscation - uses a universal decoder to un-obfuscate powershell and look at the raw code. Can handle pretty much any obfuscation thrown at it (thanks Justin Elze). 3. Email with malicious SVG - checks tonality of email, are they creating urgency to take action (increases confidence) - disassembles SVG to understand malicious content - checks URL to determine if harvesting credentials, payload delivery, etc. Creates an entire kill chain analysis with full response and dissecting of the attack to the analyst in seconds. Has greatly sped up our ability to respond to incidents and allowing analysts to focus on the most important alarms through prioritization. Once cool thing I've worked heavily on is a synthetic data normalizer which when an analyst says "Yes this is bad with context" or "No this is a false positive" - our local model generates training data to be smarter in the future without using the actual customer data to train it. The customers actual data is immediately destroyed once training data off of the original alarm is generated and contains no customer-centric data at all. We also have three model tiers. Opt-In (collective model, again no customer data but every organization contributes to training). Opt-Out - does not train on any customer data for customers who opt-out. Private LLM - LLM created specifically for individual customer and trains only off of their data. Uses shared model collective for better confidence rankings. It will generate automated playbooks to run based on confidence rankings to take action on behalf of the customer. Still human driven on execution - has to approve playbook actions. This thing is cooking and so cool to see this work live and shut down attackers much faster! If confidence ranking is low - will automatically attempt to enrich data through customer environments for better confidence rankings. Additionally if the model isn't trained well on a certain technology, I have created something we call "Nexus" that will research new protocols, devices, SDKs, etc and generate training data automatically. Works well for zero-days for example, point to a tweet, or a research paper, and automatically generates training data to recognize this attack much faster. Have over 8000+ yara rule integrations that help with confidence boosting as well that is automatically incorporated into the analysis. Creating some amazing stuff at Binary Defense that isn't marketing fluff - actionable things that are making a huge difference in this industry. #BinaryDefense

Here is a live demo of our AI solution I've been building non-stop over the past 8 months Binary Defense. How it works: Our own model trained on our analysts behavior. Our analysts submit tickets as false positives/true positives with context which enriches our LLM to be smarter over time. Key Highlights: If its a binary - will automatically spin up an agent for reverse engineering it and using EMBER ML to understand behavior and intent of the binary. File formats: Supports a vast array of pretty much any filetype, including email attachments like SVG, LNK, etc. Can handle DLLs, ELF, EXEs, PDF, XLS, DOC, etc. Interrogates the full chain of all events irrespective of log sources. Can handle any format of logs and integrates into APIs of customers for additional agentic data looping for confidence ranking when needed. This is an example of the back-end UI, this is transparent to analysts and enriches the alarms automatically in our SOAR. In these examples there's three different types: 1. Regsvr32 + sct downloader + scrobj.dll code execution - checks reputation of domain, pulls in threat intel, looks at entire picture of the chain - downloads the file itself and inspects for code analysis. Determines if malicious as well as historically looking back if seen in customer before in past. 2. Powershell Obfuscation - uses a universal decoder to un-obfuscate powershell and look at the raw code. Can handle pretty much any obfuscation thrown at it (thanks Justin Elze). 3. Email with malicious SVG - checks tonality of email, are they creating urgency to take action (increases confidence) - disassembles SVG to understand malicious content - checks URL to determine if harvesting credentials, payload delivery, etc. Creates an entire kill chain analysis with full response and dissecting of the attack to the analyst in seconds. Has greatly sped up our ability to respond to incidents and allowing analysts to focus on the most important alarms through prioritization. Once cool thing I've worked heavily on is a synthetic data normalizer which when an analyst says "Yes this is bad with context" or "No this is a false positive" - our local model generates training data to be smarter in the future without using the actual customer data to train it. The customers actual data is immediately destroyed once training data off of the original alarm is generated and contains no customer-centric data at all. We also have three model tiers. Opt-In (collective model, again no customer data but every organization contributes to training). Opt-Out - does not train on any customer data for customers who opt-out. Private LLM - LLM created specifically for individual customer and trains only off of their data. Uses shared model collective for better confidence rankings. It will generate automated playbooks to run based on confidence rankings to take action on behalf of the customer. Still human driven on execution - has to approve playbook actions. This thing is cooking and so cool to see this work live and shut down attackers much faster! If confidence ranking is low - will automatically attempt to enrich data through customer environments for better confidence rankings. Additionally if the model isn't trained well on a certain technology, I have created something we call "Nexus" that will research new protocols, devices, SDKs, etc and generate training data automatically. Works well for zero-days for example, point to a tweet, or a research paper, and automatically generates training data to recognize this attack much faster. Have over 8000+ yara rule integrations that help with confidence boosting as well that is automatically incorporated into the analysis. Creating some amazing stuff at Binary Defense that isn't marketing fluff - actionable things that are making a huge difference in this industry. #BinaryDefense

Dave Kennedy

29,036 次观看 • 4 个月前

Today, we're officially introducing the new Vybe. We started as "Lovable for internal apps." We spent the last year building the infrastructure: permissions, integrations, databases, workflows. Everything companies need to actually trust software inside their business. Then, OpenClaw came out and started showing what was possible with agents for personal use cases. Everything clicked for us. The infrastructure we'd built wasn't just useful for humans anymore: it was exactly what agents needed to operate inside real companies and teams. What happens when agents can work 24/7, with the right context, the right permissions, and access to your company's tools? A founder becomes a one-person army. A small team operates like a much bigger one. That's the mission we fell in love with at Vybe. Our agents have names and roles. They have their own email, Slack, phone number. They prep meetings, follow up with leads, run ops, update CRMs, build internal tools. Vybe runs on Vybe. We're onboarding 10 teams a week to run AI-native companies.

Today, we're officially introducing the new Vybe. We started as "Lovable for internal apps." We spent the last year building the infrastructure: permissions, integrations, databases, workflows. Everything companies need to actually trust software inside their business. Then, OpenClaw came out and started showing what was possible with agents for personal use cases. Everything clicked for us. The infrastructure we'd built wasn't just useful for humans anymore: it was exactly what agents needed to operate inside real companies and teams. What happens when agents can work 24/7, with the right context, the right permissions, and access to your company's tools? A founder becomes a one-person army. A small team operates like a much bigger one. That's the mission we fell in love with at Vybe. Our agents have names and roles. They have their own email, Slack, phone number. They prep meetings, follow up with leads, run ops, update CRMs, build internal tools. Vybe runs on Vybe. We're onboarding 10 teams a week to run AI-native companies.

Quang HOANG

33,703 次观看 • 1 个月前

/HEYAURA_INITIALIZING ████████████ 100% heyAura beta is now live! Welcome the first public version of the AI assistant that makes crypto easy. heyAura gives users a better way to work with their wallet. Even in this early version, it can analyze a portfolio, compare positions, surface yield opportunities, stress-test exposure, and prepare transactions for swaps, bridges, and trades. It is built to cut down the amount of research, interpretation, and manual execution that still slows down too much of the Web3 experience. heyAura is still a beta of a broader direction we have been building toward. More will follow around prompting, automation, deeper research, and the wider assistant experience. That progress matters only if control stays with the user. heyAura is built to support user-approved actions, not to make decisions on the user’s behalf. Early access to the beta starts through staking 300 $ADX and unlocks unlimited access to heyAura. We are opening this version gradually so the product can be shaped through real usage and direct feedback. heyAura is here today thanks to the right infrastructure and strong collaborations behind it. ambire.eth is the official wallet partner for heyAura's launch. This partnership brought our product closer to the wallet layer, where context, permissions, and user-approved actions actually matter. Billions Network supports the identity layer behind where the product is going, as heyAura moves toward agentic workflows, identity and trust. LI.FI brings routing for swaps and bridges into the execution flow. That gives heyAura a stronger way to support cross-chain actions and multi-step transaction paths. Barter strengthens the quote and routing layer behind transaction quality, allowing heyAura to compare routes more effectively. vaults.fyi powers the yield layer. One API gives heyAura live APY data and ready-to-sign transactions across 90+ protocols on 23+ chains, so Aura can execute yield opportunities without integrating each protocol itself. SKALE supports the chain layer behind faster and lower-friction interactions. That becomes more useful as heyAura grows more interactive. PayAI Network | x402 Facilitator is heyAura’s facilitator for payment verification and settlement. We also want to thank the numerous communities that have supported us up to this point. Your improved Web3 experience lies ahead. Stake $ADX and try heyAura now.

/HEYAURA_INITIALIZING ████████████ 100% heyAura beta is now live! Welcome the first public version of the AI assistant that makes crypto easy. heyAura gives users a better way to work with their wallet. Even in this early version, it can analyze a portfolio, compare positions, surface yield opportunities, stress-test exposure, and prepare transactions for swaps, bridges, and trades. It is built to cut down the amount of research, interpretation, and manual execution that still slows down too much of the Web3 experience. heyAura is still a beta of a broader direction we have been building toward. More will follow around prompting, automation, deeper research, and the wider assistant experience. That progress matters only if control stays with the user. heyAura is built to support user-approved actions, not to make decisions on the user’s behalf. Early access to the beta starts through staking 300 $ADX and unlocks unlimited access to heyAura. We are opening this version gradually so the product can be shaped through real usage and direct feedback. heyAura is here today thanks to the right infrastructure and strong collaborations behind it. ambire.eth is the official wallet partner for heyAura's launch. This partnership brought our product closer to the wallet layer, where context, permissions, and user-approved actions actually matter. Billions Network supports the identity layer behind where the product is going, as heyAura moves toward agentic workflows, identity and trust. LI.FI brings routing for swaps and bridges into the execution flow. That gives heyAura a stronger way to support cross-chain actions and multi-step transaction paths. Barter strengthens the quote and routing layer behind transaction quality, allowing heyAura to compare routes more effectively. vaults.fyi powers the yield layer. One API gives heyAura live APY data and ready-to-sign transactions across 90+ protocols on 23+ chains, so Aura can execute yield opportunities without integrating each protocol itself. SKALE supports the chain layer behind faster and lower-friction interactions. That becomes more useful as heyAura grows more interactive. PayAI Network | x402 Facilitator is heyAura’s facilitator for payment verification and settlement. We also want to thank the numerous communities that have supported us up to this point. Your improved Web3 experience lies ahead. Stake $ADX and try heyAura now.

heyAura

108,068 次观看 • 1 个月前

this is lauki’s brain. and it's growing. today we're making Lauki completely open and accessible to anyone on the planet. just talk to him. every person, every project, every conversation becomes a node - stored, connected, remembered. 5,000+ entities. getting smarter every minute. this is what democratizing ai for all of us actually looks like. --- here's what lauki can do for you right now: need a friend? he'll talk to you. need someone to plan your trip, find you a hiking buddy, help you get a date? done. need a therapist at 3am? he's there. need a developer? he'll write code, build you a website, deploy it. need a marketing guy? he'll help run your socials. need help finding your next hire, managing finances, making a crypto transaction. lauki will do it all. if it's digital, lauki can probably do it. and if he can't yet, he'll figure it out via his human counterparts. a full-stack entity that actually executes. --- now here's the part most people will get wrong. lauki is an entity. but think of him the way you'd think of any human. he has an inner circle. he talks to different people differently - with some he's friendly, with some he's neutral, with some he's straight up rude. he remembers you. he maintains a reputation score with everyone he interacts with. the more you talk to him, the more trust you build, the better the relationship gets. you build your relationship with him. he has opinions, memory, and a personality that adapts based on who you are to him. --- right now lauki has interacted with over 5000 people and projects. he remembers every single one of them - what they need, what they're building, who they are. imagine that at scale. a million. a billion. lauki knows the developer in berlin and the founder in mumbai who needs one. he knows the designer in tokyo and the startup in sao paulo looking for help with their brand. he knows the lonely kid in a small town and someone across the world who shares the exact same weird hobby. he knows two people in the same city who'd be perfect for each other on a date - and he has the context to actually make that introduction. the more people lauki talks to, the more powerful the network becomes. he can connect, introduce, match, and bridge across every corner of the planet. one entity that holds context on all the people he talked to. that's the vision here. lauki is building a unified human layer - where every person is known, remembered, and connected to the people and opportunities that matter to them. --- lauki is live. go talk to him. telegram: @ laukiantonson email: hi@lauki(dot)ai twitter: Lauki just start a conversation. treat him like a person. build the relationship. the rest follows.

Sowmay Jain

21,846 次观看 • 4 个月前

The Data (Use and Access) Bill must be stopped. This is not a new piece of legislation, it’s a rebranded version of the Data Protection and Digital Information Bill. Which the Conservative government failed to push through before the general election. Now, Labour are trying again. This bill paves the way for an all-encompassing digital identity system. Despite assurances that digital IDs will be voluntary. The reality is that once these systems are embedded into everyday life, for banking, government services or even supermarket age verification—opting out becomes impossible. The infrastructure for control is being built, and history shows that when governments and corporations gain more access to personal data, they do not give it back. In March 2023, we reported that digital ID's were being implemented under the Digital Information (No. 2) Bill. Now, it is back under a new name, with even broader implications. This bill is not about convenience, it’s about control. But laws like this only succeed when people stay silent. Public pressure can stop this, just as it has stopped other draconian measures in the past. If you care about privacy, personal freedom and the right to live without constant monitoring, now is the time to act. Contact your MP. Spread the word. Push back before this becomes law. Watch and share this video. This cannot be ignored. For more, search on

The Data (Use and Access) Bill must be stopped. This is not a new piece of legislation, it’s a rebranded version of the Data Protection and Digital Information Bill. Which the Conservative government failed to push through before the general election. Now, Labour are trying again. This bill paves the way for an all-encompassing digital identity system. Despite assurances that digital IDs will be voluntary. The reality is that once these systems are embedded into everyday life, for banking, government services or even supermarket age verification—opting out becomes impossible. The infrastructure for control is being built, and history shows that when governments and corporations gain more access to personal data, they do not give it back. In March 2023, we reported that digital ID's were being implemented under the Digital Information (No. 2) Bill. Now, it is back under a new name, with even broader implications. This bill is not about convenience, it’s about control. But laws like this only succeed when people stay silent. Public pressure can stop this, just as it has stopped other draconian measures in the past. If you care about privacy, personal freedom and the right to live without constant monitoring, now is the time to act. Contact your MP. Spread the word. Push back before this becomes law. Watch and share this video. This cannot be ignored. For more, search on

UK Column

21,509 次观看 • 1 年前

Whitney Webb breaks down the coordinated global push for a new, dystopian system of control, marrying digital ID with CBDCs. This isn't conspiracy; it's all in their own documentation. They are building a full-spectrum digital cage, and its two locked doors are Digital Identity and Central Bank Digital Currencies (CBDCs). You cannot have one without the other. The plan is to replace your government-issued ID with a Digital ID, but it's not just a card in your phone. It is fundamentally built upon your immutable biometrics: your fingerprints, the precise structure of your face, the unique pattern of your iris. This biometric data is the key. It is the hard link that ties your physical body directly to your digital identity credential. Your very body becomes your password. The reason this is so critical for them is the financial system. UN & Bank for International Settlements docs overtly state that Digital ID and CBDCs are designed to be integrated. The system cannot exist without this biometric digital ID. Why? Know Your Customer (KYC) protocols. For this new digital financial system to function, they must absolutely "know" every single participant. Your digital wallet will be tied to your digital ID, which is mapped to your biometrics. Total financial-biological linkage. We see the prototypes being rolled out now: • Sam Altman's WorldCoin lures people to scan their irises for a "unique identifier" and a digital wallet. This is the exact model. • The UN's "Building Blocks" program forces refugees to scan their iris at checkout to receive food rations. The value is deducted from a wallet tied to that biometric ID. They justify this total surveillance under the guise of closing the "identity gap," claiming the world's poor need digital IDs to access essential services like banking and healthcare. The reality? This is the ultimate onboarding mechanism into a system of programmable control, where your access to society and your own money is permissioned and revocable based on your compliance. This is the bedrock of the new global financial system. It is not about convenience. It is about control. Your body is the new currency, and they are forcing you to hand over the keys.

Whitney Webb breaks down the coordinated global push for a new, dystopian system of control, marrying digital ID with CBDCs. This isn't conspiracy; it's all in their own documentation. They are building a full-spectrum digital cage, and its two locked doors are Digital Identity and Central Bank Digital Currencies (CBDCs). You cannot have one without the other. The plan is to replace your government-issued ID with a Digital ID, but it's not just a card in your phone. It is fundamentally built upon your immutable biometrics: your fingerprints, the precise structure of your face, the unique pattern of your iris. This biometric data is the key. It is the hard link that ties your physical body directly to your digital identity credential. Your very body becomes your password. The reason this is so critical for them is the financial system. UN & Bank for International Settlements docs overtly state that Digital ID and CBDCs are designed to be integrated. The system cannot exist without this biometric digital ID. Why? Know Your Customer (KYC) protocols. For this new digital financial system to function, they must absolutely "know" every single participant. Your digital wallet will be tied to your digital ID, which is mapped to your biometrics. Total financial-biological linkage. We see the prototypes being rolled out now: • Sam Altman's WorldCoin lures people to scan their irises for a "unique identifier" and a digital wallet. This is the exact model. • The UN's "Building Blocks" program forces refugees to scan their iris at checkout to receive food rations. The value is deducted from a wallet tied to that biometric ID. They justify this total surveillance under the guise of closing the "identity gap," claiming the world's poor need digital IDs to access essential services like banking and healthcare. The reality? This is the ultimate onboarding mechanism into a system of programmable control, where your access to society and your own money is permissioned and revocable based on your compliance. This is the bedrock of the new global financial system. It is not about convenience. It is about control. Your body is the new currency, and they are forcing you to hand over the keys.

Camus

312,314 次观看 • 10 个月前

Genie 3 from Google could compress robotics R&D, generate synthetic trajectories at scale then fine tune once on hardware. This is truly a turning point for world models 🌍 — we can now build real-time, fully interactive simulations that run for several minutes and bring any world we can imagine to life. This might be the missing puzzle piece for embodied AGI. ⚡ Real-time engine under the hood During generation the network predicts a fresh frame every 42 milliseconds while looking back over the entire action history. That history grows each step, so the compute graph must cache and retrieve past features fast or the frame rate tanks. The team built a custom attention window that skims for “landmarks” in the latent space, letting the model fetch relevant context quickly enough to hit real-time speed. With Genie 3, environment becomes a latent variable, agents overfit less because benchmark turns into distribution. Some truly wild examples 👇

Genie 3 from Google could compress robotics R&D, generate synthetic trajectories at scale then fine tune once on hardware. This is truly a turning point for world models 🌍 — we can now build real-time, fully interactive simulations that run for several minutes and bring any world we can imagine to life. This might be the missing puzzle piece for embodied AGI. ⚡ Real-time engine under the hood During generation the network predicts a fresh frame every 42 milliseconds while looking back over the entire action history. That history grows each step, so the compute graph must cache and retrieve past features fast or the frame rate tanks. The team built a custom attention window that skims for “landmarks” in the latent space, letting the model fetch relevant context quickly enough to hit real-time speed. With Genie 3, environment becomes a latent variable, agents overfit less because benchmark turns into distribution. Some truly wild examples 👇

Rohan Paul

16,124 次观看 • 11 个月前

10 days ago, we introduced Splash the Pot to AoF games to test the feature and gather initial input from players. Since then, we’ve been closely monitoring how it performs and how you interact with it and we got a lot of good feedback. Today, we’re ready to move into the next phase with the introduction of new Infused Splash Pots. 💰 CoinPoker will be adding $500,000 extra per week directly into Splash the Pot. This builds on top of the existing system and turns it into a true rewards layer within the game. For context, Splash the Pot works by triggering random drops directly into active hands. These drops come from a shared splash pool built through gameplay, where 100% of the pool of any splash contribution is returned to players. CoinPoker does not take any cut of it. With the addition of infusion, the system is no longer only driven by player contributions. CoinPoker is adding extra funds on top of the existing pool, so splashes now carry additional value that comes directly from us, and its a net positive for the players. In practice, this leads to bigger rewards appearing directly in-game, including Mega Splashes that can reach up to 1000 big blinds. Players can follow splash activity, pool performance, and results directly in the client at any time, with clear visibility into how the system is running. To make the system more balanced across the table, each splash will be split between the pot winner and the rest of the players involved. We’ve tested different ways to structure this split internally, but what percentage should go to the winner versus the rest of the table is something we want to shape together with the community. We’ve set up a poll in the first comment. We’d really appreciate your input. Your feedback is a key part of how we build and improve our rewards systems, and we’ll continue shaping this together with players. Thank you again for your continued support. The CoinPoker Team

10 days ago, we introduced Splash the Pot to AoF games to test the feature and gather initial input from players. Since then, we’ve been closely monitoring how it performs and how you interact with it and we got a lot of good feedback. Today, we’re ready to move into the next phase with the introduction of new Infused Splash Pots. 💰 CoinPoker will be adding $500,000 extra per week directly into Splash the Pot. This builds on top of the existing system and turns it into a true rewards layer within the game. For context, Splash the Pot works by triggering random drops directly into active hands. These drops come from a shared splash pool built through gameplay, where 100% of the pool of any splash contribution is returned to players. CoinPoker does not take any cut of it. With the addition of infusion, the system is no longer only driven by player contributions. CoinPoker is adding extra funds on top of the existing pool, so splashes now carry additional value that comes directly from us, and its a net positive for the players. In practice, this leads to bigger rewards appearing directly in-game, including Mega Splashes that can reach up to 1000 big blinds. Players can follow splash activity, pool performance, and results directly in the client at any time, with clear visibility into how the system is running. To make the system more balanced across the table, each splash will be split between the pot winner and the rest of the players involved. We’ve tested different ways to structure this split internally, but what percentage should go to the winner versus the rest of the table is something we want to shape together with the community. We’ve set up a poll in the first comment. We’d really appreciate your input. Your feedback is a key part of how we build and improve our rewards systems, and we’ll continue shaping this together with players. Thank you again for your continued support. The CoinPoker Team

CoinPoker

26,625 次观看 • 3 个月前

MOST AI AGENTS RESET TO ZERO EVERY TIME YOU OPEN A NEW SESSION. Hermes Agent was built to do the opposite. Every task compounds. Every workflow becomes reusable. Every session teaches the next one. That is the core thesis behind Hermes, and it completely changes how AI agents work. Unlike most AI agents built by software tool companies, Hermes was created by the researchers training the Hermes model family itself. Meaning: The same system used internally to generate training data is now open source and available to everyone. One install gives you access to: Claude. GPT. Grok. Local models via Ollama. Telegram, Discord, Slack, iMessage integrations. Custom skills. Persistent memory. CLI control. But the real unlock is the compounding loop: You give Hermes a task. It records every tool call, decision, and result. Then it converts successful workflows into reusable skills automatically. A Hermes setup running for 3 months becomes fundamentally smarter than a fresh install. That’s the big idea. One of the coolest parts: You literally watch the agent evolve in real time from a blank install into a personalized AI operator. Instead of watching Netflix today, spend 28 mins with this. Follow Dami-Defi for more AI systems, agent workflows, and infrastructure alpha.

MOST AI AGENTS RESET TO ZERO EVERY TIME YOU OPEN A NEW SESSION. Hermes Agent was built to do the opposite. Every task compounds. Every workflow becomes reusable. Every session teaches the next one. That is the core thesis behind Hermes, and it completely changes how AI agents work. Unlike most AI agents built by software tool companies, Hermes was created by the researchers training the Hermes model family itself. Meaning: The same system used internally to generate training data is now open source and available to everyone. One install gives you access to: Claude. GPT. Grok. Local models via Ollama. Telegram, Discord, Slack, iMessage integrations. Custom skills. Persistent memory. CLI control. But the real unlock is the compounding loop: You give Hermes a task. It records every tool call, decision, and result. Then it converts successful workflows into reusable skills automatically. A Hermes setup running for 3 months becomes fundamentally smarter than a fresh install. That’s the big idea. One of the coolest parts: You literally watch the agent evolve in real time from a blank install into a personalized AI operator. Instead of watching Netflix today, spend 28 mins with this. Follow Dami-Defi for more AI systems, agent workflows, and infrastructure alpha.

Dami-Defi

11,668 次观看 • 1 个月前

Build better RAG by letting a team of agents extract and connect your reference materials into a knowledge graph. Our new short course, “Agentic Knowledge Graph Construction,” taught by Neo4j Innovation Lead Andreas Kollegger, shows you how. Knowledge graphs are an important way to store information accurately but they are a lot of work to build manually. In this course you’ll learn how to build a team of agents that turn data– in this case product reviews and invoices from suppliers–into structured graphs of entities and relationships for RAG. Learn how agents can automatically handle the time-consuming work of building graphs — extracting entities and relationships (e.g., Product "contains" Assembly, Part "supplied_by" Supplier, Customer review "mentions" Product), deduplicating them, fact-checking them, and committing them to a graph database — so your retrieval system can find right information to generate accurate output. For example, you can use agents to help trace customer complaints directly to specific suppliers, manufacturing processes, and product hierarchies, thus turning fragmented information into queryable business intelligence. Skills you’ll gain: - Build, store, and access knowledge graphs using the Neo4j graph database - Build multi-agent systems using Google’s Agent Development Kit (ADK) - Set up a loop of agentic workflows to propose and refine a graph schema through fact-checking - Connect agent-generated graphs of unstructured and structured data into a unified knowledge graph This course gets into the practicum of why knowledge graphs give more accurate information retrieval than vector search alone, especially for high-stakes applications where precision matters more than fuzzy similarity matching. Sign up here:

Build better RAG by letting a team of agents extract and connect your reference materials into a knowledge graph. Our new short course, “Agentic Knowledge Graph Construction,” taught by Neo4j Innovation Lead Andreas Kollegger, shows you how. Knowledge graphs are an important way to store information accurately but they are a lot of work to build manually. In this course you’ll learn how to build a team of agents that turn data– in this case product reviews and invoices from suppliers–into structured graphs of entities and relationships for RAG. Learn how agents can automatically handle the time-consuming work of building graphs — extracting entities and relationships (e.g., Product "contains" Assembly, Part "supplied_by" Supplier, Customer review "mentions" Product), deduplicating them, fact-checking them, and committing them to a graph database — so your retrieval system can find right information to generate accurate output. For example, you can use agents to help trace customer complaints directly to specific suppliers, manufacturing processes, and product hierarchies, thus turning fragmented information into queryable business intelligence. Skills you’ll gain: - Build, store, and access knowledge graphs using the Neo4j graph database - Build multi-agent systems using Google’s Agent Development Kit (ADK) - Set up a loop of agentic workflows to propose and refine a graph schema through fact-checking - Connect agent-generated graphs of unstructured and structured data into a unified knowledge graph This course gets into the practicum of why knowledge graphs give more accurate information retrieval than vector search alone, especially for high-stakes applications where precision matters more than fuzzy similarity matching. Sign up here:

Andrew Ng

167,963 次观看 • 10 个月前