Hi, I'm Flavio Milan.

This is my space for thinking in writing. I keep what I study, read and notice here.

I write to understand. Long articles, short notes and reading notes, on no fixed schedule. More about me.

Latest entries

Full archive

June 2026

  1. Inside the Fackel harness: parallel agent lanes in a terminal

    Article8 min read

    How Fackel's interactive harness renders parallel pentest agents in separate lanes, handles inline approvals without freezing, and survives Ctrl-C — the design choices behind the terminal.

April 2026

  1. Ultralearning in a Polarized Labor Market

    Article9 min read

    An essay on education, self-study, and deliberate learning as a technical and human response to an increasingly polarized labor market.

  2. npm's supply chain is broken — the Axios attack explains why

    Article16 min read

    Technical analysis of the Axios npm supply chain attack in March 2026: what happened, what the malware did, why CI/CD is the real target, and how to protect yourself.

March 2026

  1. LangGraph, CrewAI, and Agno: getting started with AI agents in Python

    Article12 min read

    A practical guide to getting started with AI agents. Three frameworks, the same problem, real examples, and an honest comparison.

  2. When AI Stops Being a Tool and Becomes an Attack Surface

    Article15 min read

    When AI becomes an attack surface: prompt injection, end-to-end attack chains, at-risk architectures, and defensive actions.

  3. Fackel: an autonomous pentest framework powered by ReAct agents

    Article5 min read

    Fackel: a multi-agent pentest framework where LLMs decide strategy. Architecture walkthrough, design decisions, and lessons learned.

February 2026

  1. Device Code Phishing + Vishing: How Attackers Compromise Microsoft Entra Accounts Using Legit Login Pages

    Article6 min read

    Device code phishing combined with vishing targeting Microsoft Entra: how the OAuth flow gets abused, what to monitor, and how to mitigate.

  2. The State of the Art in AI Agents (2026): What ‘Modern’ Actually Means

    Article6 min read

    A practical overview of modern AI agent systems: tool use, retrieval, memory, verification, multi-agent patterns, evaluation, and security.

  3. The chain rule behind autoregressive models

    Article5 min read

    Autoregressive models are just the probability chain rule plus a conditional model. Here’s the mental model, the math, and what training is really doing.

  4. Decision memos that prevent circular debates

    Article1 min read

    A lightweight memo format that clarifies the call, exposes trade-offs, and speeds up execution.

  5. Security Implications of Probabilistic Reasoning in Generative AI

    Article6 min read

    A rigorous analysis of how probabilistic reasoning in generative models shapes security risk, failure modes, and robustness.

  6. Separation of Responsibilities in Spring-Based Systems: What Kotlin Makes Explicit

    Article7 min read

    How Kotlin's type system sharpens responsibility boundaries in Spring-style architectures without replacing architectural discipline.

Topics

New entries arrive by RSS.