Agentic AI

Latest episode

Episodes

1. What is JEV from TypeSafe AI? How We implemented Agentic SOC use cases and other use cases? (Github Repo URL Included in Paid Section)
   Sep 21, 2026
2. Chapter 9: Ultra-Long Context Mastery: Dual-Chunk Attention, YaRN & Sparse Routing
   Sep 20, 2026
3. Chapter 8: Test-Time Compute & Reasoning Dynamics: DeepSeek-V4-Pro, GLM-5.3 & Kimi K3
   Sep 19, 2026
4. Chapter 7: Serving Mega-MoE at Scale: Colossus Interconnects, Expert Parallelism & DualPipe
   Sep 18, 2026
5. GPT-6 Astra plus Kimi K3 Swarm: route depth and width before you pay frontier rates
   Sep 17, 2026
6. OpenAI’s Defense Factory turns vulnerability work into a continuous five-stage agent loop
   Sep 16, 2026
7. We Can’t Sleepwalk Through the AI Transition
   Sep 15, 2026
8. Chapter 6: Disaggregated Serving Architectures: Mooncake, DistServe & vLLM V1
   Sep 15, 2026
9. Nadella’s AI moat is the learning loop your company owns, not the model you rent
   Sep 14, 2026
10. CLAUDE.md Modernization and Prefix-Stable KV Caching for Claude Code
    Sep 13, 2026
11. Chapter 5: Hardware-Aware Attention Kernels: FlashAttention-3, FlashDecoding & TPU Pallas
    Sep 12, 2026
12. Agentic AI: What Caught My Attention This Week
    Sep 12, 2026
13. AI Targeting and Weapons Software: What Anthropic's New Evals Actually Measure
    Sep 11, 2026
14. Chapter 4: Extreme Quantization & Precision Engineering: Blackwell FP4, Native FP8 & Unsloth
    Sep 10, 2026
15. Chapter 3: Next-Gen Speculative Decoding: Multi-Token Prediction (MTP), EAGLE-2 & IndexShare
    Sep 8, 2026
16. Inside the Book: Graph Engineering for Agentic AI Systems, Chapter by Chapter
    Sep 7, 2026
17. Chapter 2: The KV Cache Frontier: Hybrid Compressed Sparse Attention (DeepSeek-V4 CSA/HCA) & MLA, Global Prefix Caching & KVShare
    Sep 6, 2026
18. Astra or GPT6: Inside OpenAI's First Critical-Tier Model
    Sep 4, 2026
19. Upcoming Keynote on “Hands-On Graph Engineering with Claude Code Course”
    Sep 3, 2026
20. Anthropic’s Fable 5.1 guide reads like a manual for agent product design, not a collection of prompt tricks
    Sep 3, 2026
21. The Harness Advantage in Autonomous Red Teaming: Why Frontier LLMs Alone Fail Offensive Security and How RidgeGen Solves the Alignment Dilemma
    Sep 2, 2026
22. Chapter 1: The Physics of LLM Inference: Memory Walls, Arithmetic Intensity, and Compute Ceilings
    Aug 31, 2026
23. Multi-Agent Design Patterns: Architectural Topologies, Failure Modes, and Production Hardening
    Aug 29, 2026
24. Grok Bot Is Here. MAESTRO Shows Where the Real Risks Are.
    Aug 28, 2026
25. The Gateway Is Not the Identity: Attested Trust for Agentic AI
    Aug 26, 2026
26. Announcing Humanoid Robots and Physical AI Book by Springer: The Whole-System Guide to the Next Industrial Revolution
    Aug 24, 2026
27. Chapter 1: The Physics of LLM Inference: Roofline Models, Memory Walls & The Prefill-Decode Dichotomy
    Aug 23, 2026
28. Announcing the 10-Part Substack Series: The Physics & Engineering of Frontier LLM Inference (2026 Edition)
    Aug 23, 2026
29. How Claude’s Text Watermarking Works
    Aug 23, 2026
30. Proof-of-Control for Model Context Protocol
    Aug 22, 2026
31. From Software Engineering to Harness Engineering: What OpenAI's Codex Actually Builds
    Aug 21, 2026
32. FOR IMMEDIATE RELEASE: OWASP Publishes Agentic Skills Top 10 v1.0
    Aug 17, 2026
33. Harness Engineering: Design Patterns for Securing Long-Horizon Multi-Agent AI Systems
    Aug 13, 2026
34. 40% OFF: Hands-On Harness Engineering with Claude
    Aug 11, 2026
35. Black Hat and DEF CON 34 Trip Report: What Vegas Actually Shipped in Agentic AI Security
    Aug 11, 2026
36. Coding Agent Security: Lessons from Claude Code, Cowork, Codex, and Copilot in the Wild
    Aug 8, 2026
37. Inside the 1-Bit LLM: How Bonsai Fits a 27B Model on a Phone
    Aug 7, 2026
38. Part 1: A Software Factory Agentic Skill for Greenfield Builds
    Aug 2, 2026
39. MAESTRO Analysis of OpenAI and Anthropic Agent Hacking Incidents
    Aug 1, 2026
40. One Week, Three Conferences: My Las Vegas AI Security Itinerary
    Jul 31, 2026
41. Harness Engineering as the Umbrella Discipline
    Jul 31, 2026
42. Join My Live "Hands-On Harness Engineering with Claude" Workshop (August 20, 2026)
    Jul 30, 2026
43. We Scored 4,570 Agents Against OWASP AIVSS and CSA MAESTRO
    Jul 28, 2026
44. Agentic AI CVEs: Anatomy of a New Attack Surface
    Jul 26, 2026
45. The Hidden Tax on AI Is Coordination
    Jul 23, 2026
46. Microsoft's Approach to LLM: MAI-Thinking-1
    Jun 3, 2026