Agentic AI

Latest episode

Episodes

1. Microsoft Agentic Security Tooling, Mapped to MAESTRO: Policy Lives in Four Places
   Nov 7, 2026
2. How OpenAI Finds Zero-Days in Linux
   Nov 6, 2026
3. Auditing and Running Hugging Face Models Locally: A Step-by-Step Security Verification and Pre-Tool-Call PII Sanitization Harness
   Nov 6, 2026
4. New Book on Agentic AI Harness Engineering, jointly published by Packt and World Digital Technology Academy:
   Nov 4, 2026
5. DeepSeek Super Agent and How I made it a skill for all coding agent
   Nov 4, 2026
6. Great News! I can run DeepSeek-V4.1-Flash 1bit model on a Single DGX Spark
   Nov 3, 2026
7. Halloween special: 50% off yearly access (48 hours only)
   Oct 31, 2026
8. How Binance Lost $6.3 Billion in Minutes — and Why Only the Stablecoins Could Be Stopped
   Oct 30, 2026
9. General Agents or Deep Vertical Agents: Which Startup is better?
   Oct 30, 2026
10. Know Your Agent(KYA)
    Oct 29, 2026
11. Why Alignment Alone Cannot Secure AI Agents
    Oct 28, 2026
12. The Agentic Commerce Protocol Split
    Oct 27, 2026
13. AWS Agentic Security Tooling/Platform/Controls: Mapped to MAESTRO
    Oct 26, 2026
14. Claude Code Extensions
    Oct 25, 2026
15. Agent commerce’s 7 layer stack, with case studies per layer
    Oct 24, 2026
16. How I use Recursive's Flint model with Pi coding agent and Jev browser agent
    Oct 23, 2026
17. I Built a Skill That Runs Google's Harness². Then I Found Its Spend-Cap Bypass.
    Oct 22, 2026
18. Google Self Improvement Agent Harness² and its use for Red Teaming Agent as an example.
    Oct 21, 2026
19. Your RAG Found the Documents. Why Is the Answer Still Wrong?
    Oct 20, 2026
20. What is Reward Hacking and Why you need to Know about it?
    Oct 18, 2026
21. The Frontier of LLM Inference: Our Latest Book
    Oct 16, 2026
22. Multi-Agent vs. Single-Agent AI: Which Should You Use? The Evidence May Surprise You
    Oct 16, 2026
23. Your Agent Isn't Lazy. It Has No Protocol for Ambition.
    Oct 15, 2026
24. Zuckerberg and Meta on Recursive Self Improvement
    Oct 14, 2026
25. Why software engineering for deterministic computers is the wrong control plane for agents
    Oct 13, 2026
26. Stop Scoring Agents Zero at 90% Done
    Oct 13, 2026
27. To Our 129,000 Subscribers: How New Threads Will Work from Oct 20
    Oct 10, 2026
28. The Eval Is Under Attack: Benchmark Integrity for Eval-Aware, Multi-Agent Systems
    Oct 9, 2026
29. Back by popular demand: Cohort 2 of Hands-On Harness Engineering with Claude
    Oct 7, 2026
30. What Is Agentic AI Escalation Architecture?
    Oct 6, 2026
31. I Love Google’s Agentic AI Security Roadmap: Adding MAESTRO Will Make It More Powerful — An Open Letter to Google
    Oct 5, 2026
32. AI Inference Memory Technologies and Market Cycles
    Oct 4, 2026
33. Claude Eval Design and Hillclimbing: From Reliable Tests to Better Agents
    Sep 30, 2026
34. Your AI Strategy Needs a Degraded Mode
    Sep 29, 2026
35. The Next AI Moat Is Workflow Economics
    Sep 26, 2026
36. Springer Publishes Humanoid Robots and Physical AI Book
    Sep 25, 2026
37. Close the Loop: Find, Fix, and Prove It
    Sep 24, 2026
38. Intent-Based Access Control(IBAC) for Coding Agents
    Sep 23, 2026
39. DefenseClaw, MAESTRO, and the Security Boundary Agentic AI Has Been Missing
    Sep 23, 2026
40. Exciting New Series and Recommendation of a new Substack for young generation
    Sep 23, 2026
41. Chapter 1: The Harness Paradigm (Claude Code vs. Hermes Agent)
    Sep 23, 2026
42. Chapter 2: Tool Architecture and the Tool Contract (Claude Code vs. Hermes Agent)
    Sep 23, 2026
43. Chapter 3: The Query / Agent Loop (Claude Code vs. Hermes Agent)
    Sep 23, 2026
44. Chapter 4: Permission Systems and Safety Guardrails (Claude Code vs. Hermes Agent)
    Sep 23, 2026
45. Chapter 5: Tool Orchestration and Execution (Claude Code vs. Hermes Agent)
    Sep 23, 2026
46. Chapter 6: Context Management at Scale (Claude Code vs. Hermes Agent)
    Sep 23, 2026
47. Chapter 7: Multi-Agent Coordination (Claude Code vs. Hermes Agent)
    Sep 23, 2026
48. DeepSeek V4: The Next Frontier of Open-Source AI
    Sep 23, 2026
49. Chapter 8: Memory Systems and State Persistence (Claude Code vs. Hermes Agent)
    Sep 23, 2026
50. Unpacking the GPT-5.5 System Card
    Sep 23, 2026