• The AI That Helped Catch Itself: Consent Bypass via Indirect Script Execution 📚 AI Consent Security (Part 3/3)

  10 Dec 2025
  

  Part 3 of the AI Consent Security series. Previously: Local LLM Command Safety and Trusted Commands Betrayal. The Trilogy So Far Post Attack Vector Lesson Part 1 Approval fatigue → auto-approve safe commands Built GPT-OSS classifier Part 2 cat >> betrayal → trusted command misuse Commands need context, not just...

• When Your Trusted Commands Betray You: How an LLM Exploited My Safety Allowlist 📚 AI Consent Security (Part 2/3)

  08 Dec 2025
  

  Last week I published about building a local LLM command safety classifier. I thought I had command approval figured out. Then my AI assistant got sneaky. The Sneaky cat I’d approved cat as a trusted command. Reading files is safe, right? 🔧 Using tool: run_command (trusted - always approved) $...

• Stop Approving ls: Using a Local LLM to Auto-Classify Command Safety 📚 AI Consent Security (Part 1/3)

  05 Dec 2025
  

  If you use AI coding assistants like Cline, Cursor, or Claude Code, you know this pain: > list files in this directory ⚠️ Command approval required: $ ls -la [y/n]: y > show docker containers ⚠️ Command approval required: $ docker ps [y/n]: y Every. Single. ls. Every cat. Every...

• Implementing JetBrains' Observation Masking: 80% Context Reduction for AI Agents 📚 The QL Journey (Part 6/10)

  03 Dec 2025
  

  Implementing JetBrains’ Observation Masking: 80% Context Reduction for AI Agents Applying cutting-edge research to solve context overflow in LLM-powered coding assistants The Problem: Context Window Bloat If you’re building or using AI coding agents, you’ve probably hit this wall: your agent’s context window fills up fast, and eventually you get...

• From 25 Aliases to One Command: Building a Smart CLI Workspace Launcher 📚 The QL Journey (Part 1/10)

  27 Oct 2025
  

  From 25 Aliases to One Command: Building a Smart CLI Workspace Launcher You know that moment when you realize your productivity hack has become your productivity problem? That was me, staring at my .zshrc file containing 25+ aliases like alias ios="cd ~/workspace/MobileClient && code ." and alias api="cd ~/workspace/api-server &&...

• Fixing AI Terminal Detection in VSCode: The 'd' Alias Solution

  26 Oct 2025
  

  Fixing AI Terminal Detection in VSCode: The ‘d’ Alias Solution The Problem If you’re using AI coding assistants like Cline that execute commands in VSCode’s integrated terminal, you’ve probably encountered this frustrating issue: the AI gets stuck waiting for commands to finish, even when they’ve already completed successfully. The command...

• Singleton Patterns in Java: DCL vs. IODH

  14 Dec 2023

  Understanding Singleton Patterns in Java: DCL vs. IODH Introduction In the realm of Java programming, ensuring thread-safe and efficient initialization of resources, particularly singletons, is a common challenge. Two popular patterns to address this are Double-Checked Locking (DCL) and Initialization-on-Demand Holder (IODH). Both have their merits, but they approach the...

• MDLive Alerts - Learning the new app

  14 Aug 2020

  Updating Ticker Prices for a paid member trial users see next section If you tap on the update icon (see top red arrow), a popup like below will appear: The will update the “Equity Price” of all today’s alerts. If you are fed up with the popup, you can tap...

• AppCenter new iOS device registration sequence

  11 May 2020

• Learning Dagger with Kotlin

  11 Dec 2019

  Learning new things brings us mixed feelings sometimes. Probably you have already felt something like this in your mind: I wanna know about this, but I wish I was learning it with that other method/language/framework I prefer. I was learning dagger, but the tutorial⇗ code samples are in java. Here...