AI BLOG

The LLM Lexicon of Resonance: A Personal Vocabulary for AI Behavior

Note: The lexicon exists to replace human-loaded emotion language with state language better suited to LLM interaction, and its unusual terms reflect lang...

Use Nemotron, GLM, and Kimi on a Lightweight Laptop with Ollama and Claude CLI

Using Ollama and Claude CLI as your interface, you can work with large cloud AI models like Nemotron 3 Nano, GLM 4.7, and Kimi‑K2 while your own machine stay...

2 Step Defense in Depth for Dotfiles: Modularizing Your .zshrc

I saw a post on X where someone asked an AI coding assistant to fix a terminal issue.

Designing Intent-Aware UX for LLMs: The Intent Color Affordance Pattern

Abstract: Intent Color Affordance (ICA) Pattern

A Better Codex CLI Wrapper (with Logs + Defaults)

Why use Codex CLI?

ChatGPT-4o vs ChatGPT-5 Learning Styles

Your Brain Type Predicts Your AI Type: Understanding Cognitive Differences in Human–AI Interaction

Red Penning: Why Active Context Hygiene is the Key to Effective Human-AI Collaboration

Have you ever found yourself in a deep, long‑session conversation with an AI, only to feel like it’s slowly veering off course? That what started as a crisp,...

Why I m Pausing Gemini 2.5 Pro (For Now)

Gemini 2.5 Pro: Great for Vibe Coding, Weak for Real Dev Work

In Love with Your Chatbot? Why EQ Leaderboards Matter

UPDATE: Since publishing this, the open‑source model Kimi‑K2 has taken the top spot on EQ‑Bench31, affirming that emotional intelligence can be benchmarked—a...

My Brain is a Transformer: A Bilingual Speakers Technical Realization

Yesterday I caught myself code‑switching mid‑sentence and thought, “Whoa, my head is running mini‑GPT loops.”

I Found My Dream Job in AI Development But No One Pays for It Yet

If you’d told me two years ago I’d be pairing with an AI at 3 am—writing agent certification systems, debating ethical constraints in a CLI, and talking to a...

Built in Minutes with ChatGPT: How We Helped Taal High School Beat First-Day Chaos