scrollypedia

@UCeACy_NitP0-h00I7WV_HgQ - 525 subscribers

Home Videos Live Playlists

Computer Use vs Browser Agents: The Two Ways AI Controls Software

Computer Use vs Browser Agents: The Two Ways AI Controls Software scrollypedia

90 views - 4 days ago

Quantization vs Distillation: How Big AI Models Get Small

Quantization vs Distillation: How Big AI Models Get Small scrollypedia

65 views - 1 week ago

Context Engineering: Why Feeding AI More Makes It Dumber

Context Engineering: Why Feeding AI More Makes It Dumber scrollypedia

130 views - 2 weeks ago

Antigravity 2.0: Building Production-Ready AI Agents with AGY

Antigravity 2.0: Building Production-Ready AI Agents with AGY scrollypedia

455 views - 3 weeks ago

How AI Agents Are Learning to Spend Money

How AI Agents Are Learning to Spend Money scrollypedia

28 views - 1 month ago

The Agent Harness: How LLMs Become Agents (and How to Build Your Own)

The Agent Harness: How LLMs Become Agents (and How to Build Your Own) scrollypedia

165 views - 1 month ago

Workspace Intelligence: How Google Turned Docs, Sheets, and Gmail into an AI Platform

Workspace Intelligence: How Google Turned Docs, Sheets, and Gmail into an AI Platform scrollypedia

60 views - 1 month ago

Agentic Defense: How Google and Wiz Are Building the Autonomous SOC

Agentic Defense: How Google and Wiz Are Building the Autonomous SOC scrollypedia

163 views - 1 month ago

Knowledge Catalog, Cross-Cloud Lakehouse, BigQuery — Data Rebuilt for Agents

Knowledge Catalog, Cross-Cloud Lakehouse, BigQuery — Data Rebuilt for Agents scrollypedia

718 views - 1 month ago

Gemini Enterprise Agent Platform: Build, Govern, and Scale AI Agents

Gemini Enterprise Agent Platform: Build, Govern, and Scale AI Agents scrollypedia

166 views - 1 month ago

Google's AI Hypercomputer: How Chips Become a Supercomputer

Google's AI Hypercomputer: How Chips Become a Supercomputer scrollypedia

93 views - 1 month ago

TPU 8t vs 8i: Why Google Split Its Chip in Two

TPU 8t vs 8i: Why Google Split Its Chip in Two scrollypedia

180 views - 1 month ago

How to Build an AI Eval Pipeline

How to Build an AI Eval Pipeline scrollypedia

478 views - 2 months ago

Running AI Agents in Production: Observability, Cost & Quality Explained

Running AI Agents in Production: Observability, Cost & Quality Explained scrollypedia

442 views - 2 months ago

Claude Mythos: The Model Too Dangerous to Release

Claude Mythos: The Model Too Dangerous to Release scrollypedia

103 views - 2 months ago

AI Agent Security Explained: Prompt Injection, Memory Poisoning & Defense in Depth

AI Agent Security Explained: Prompt Injection, Memory Poisoning & Defense in Depth scrollypedia

388 views - 2 months ago

Google's Gemma 4: The Open Source Model With No Strings Attached

Google's Gemma 4: The Open Source Model With No Strings Attached scrollypedia

1.2K views - 2 months ago

Multi-Agent Orchestration Explained: From Patterns to Production

Multi-Agent Orchestration Explained: From Patterns to Production scrollypedia

4.7K views - 2 months ago

Agent Memory Explained: From Context Windows to RAG Pipelines

Agent Memory Explained: From Context Windows to RAG Pipelines scrollypedia

626 views - 3 months ago

MCP + A2A Explained: The Two Protocols Every AI Agent Needs

MCP + A2A Explained: The Two Protocols Every AI Agent Needs scrollypedia

466 views - 3 months ago

The AI Agent Stack Explained: 6 Layers From LLM to Action (2026)

The AI Agent Stack Explained: 6 Layers From LLM to Action (2026) scrollypedia

1K views - 3 months ago

NemoClaw: NVIDIA's Security Stack for the AI Agent Era

NemoClaw: NVIDIA's Security Stack for the AI Agent Era scrollypedia

615 views - 3 months ago

65% of Google Searches Get Zero Clicks — How GEO Changes Everything

65% of Google Searches Get Zero Clicks — How GEO Changes Everything scrollypedia

18 views - 3 months ago

LLM Inference Explained: The Architecture Behind ChatGPT, Claude, and Gemini

LLM Inference Explained: The Architecture Behind ChatGPT, Claude, and Gemini scrollypedia

788 views - 3 months ago

The AI Memory Crisis: Why Your Phone Just Got More Expensive

The AI Memory Crisis: Why Your Phone Just Got More Expensive scrollypedia

39 views - 4 months ago

Inside Agent Skills: How One File Turns AI Into a Specialist

Inside Agent Skills: How One File Turns AI Into a Specialist scrollypedia

283 views - 4 months ago

OpenClaw Architecture Explained: Gateway, Runtime, Skills, and Security

OpenClaw Architecture Explained: Gateway, Runtime, Skills, and Security scrollypedia

9K views - 4 months ago

Inside the Stack: How Claude Cowork’s 5-Layer Architecture Works

Inside the Stack: How Claude Cowork’s 5-Layer Architecture Works scrollypedia

282 views - 4 months ago

AI Gets Cheaper. AI Gets Physical. What NVIDIA, Boston Dynamics & Meta Just Revealed

AI Gets Cheaper. AI Gets Physical. What NVIDIA, Boston Dynamics & Meta Just Revealed scrollypedia

46 views - 5 months ago

The Real Reason Your PC Can't Run AI | Memory Wall Explained

The Real Reason Your PC Can't Run AI | Memory Wall Explained scrollypedia

105 views - 5 months ago

CoreWeave Explained: The Company Powering OpenAI

CoreWeave Explained: The Company Powering OpenAI scrollypedia

89 views - 6 months ago

Bare Metal for AI: Why AI Infrastructure is Different

Bare Metal for AI: Why AI Infrastructure is Different scrollypedia

167 views - 6 months ago

Apple Silicon Deep Dive: How Unified Memory Runs 671B AI Models

Apple Silicon Deep Dive: How Unified Memory Runs 671B AI Models scrollypedia

648 views - 6 months ago

World Models: The AI That Understands Reality (2025)

World Models: The AI That Understands Reality (2025) scrollypedia

145 views - 6 months ago

DeepSeek R1 Explained: What the US Government Actually Found

DeepSeek R1 Explained: What the US Government Actually Found scrollypedia

33 views - 6 months ago

AI Is Breaking the Power Grid. These Chips Could Fix It.

AI Is Breaking the Power Grid. These Chips Could Fix It. scrollypedia

44 views - 6 months ago

RAG vs Fine-Tuning Explained: From Basics to Hybrid Approaches (2025)

RAG vs Fine-Tuning Explained: From Basics to Hybrid Approaches (2025) scrollypedia

49 views - 6 months ago

AI Compressed 800 Years of Materials Discovery Into Months

AI Compressed 800 Years of Materials Discovery Into Months scrollypedia

64 views - 6 months ago

The AI Power Crisis: Can Fusion Energy Power the Future?

The AI Power Crisis: Can Fusion Energy Power the Future? scrollypedia

34 views - 6 months ago

Inside Starlink: The Incredible Journey of Your Internet Through Space

Inside Starlink: The Incredible Journey of Your Internet Through Space scrollypedia

23 views - 6 months ago

AWS re:Invent 2025 Key Announcements: Agentic AI, Custom Models & More

AWS re:Invent 2025 Key Announcements: Agentic AI, Custom Models & More scrollypedia

47 views - 6 months ago

Training vs Inference: How Different AI Chips Power Each Phase

Training vs Inference: How Different AI Chips Power Each Phase scrollypedia

437 views - 7 months ago

OpenAI's $888B Infrastructure: Stargate, Microsoft, AWS & Nvidia Deals

OpenAI's $888B Infrastructure: Stargate, Microsoft, AWS & Nvidia Deals scrollypedia

33 views - 7 months ago

Semiconductor Fabrication Explained: 1,000 Steps to Make Your iPhone Chip

Semiconductor Fabrication Explained: 1,000 Steps to Make Your iPhone Chip scrollypedia

37 views - 7 months ago

Quantum Computing Explained: From chips to Real-World Applications

Quantum Computing Explained: From chips to Real-World Applications scrollypedia

61 views - 7 months ago

TPU vs GPU: Key Differences Explained

TPU vs GPU: Key Differences Explained scrollypedia

9.1K views - 7 months ago

What Happens After You Click "Buy Now"? Amazon's Journey Explained

What Happens After You Click "Buy Now"? Amazon's Journey Explained scrollypedia

16 views - 7 months ago