-
Why Every Writer Needs a Local LLM (and How to Set One Up)
How writers can use a local LLM on Mac for manuscript feedback, line editing, and research summarization. Ollama setup guide for non-technical writers, model recommendations, and two ready-to-use editor system prompts.
-
JetBrains AI Assistant: Scoping Junie tasks by module to keep review tractable
A field-tested take on scoping Junie tasks by module to keep review tractable with JetBrains AI Assistant: what it rewards, where it breaks, and how to keep the workflow honest.
-
Test Data: The Unsung Hero of the QA World
Test data is the foundation of quality assurance. Learn why test data management matters, common pitfalls to avoid, and practical strategies for creating.
-
The Real Cost of Training an AI Model That Nobody Wants You to Know
AI training costs dominate headlines, but inference, annotation, safety red-teaming, and human labelers are where the real economics of AI get brutal.
-
AI Video Upscaling on Mac — Restore Old Family Videos This Weekend
How to restore old family videos with AI on Apple Silicon — Topaz Video AI deinterlacing and 480p to HD upscaling with realistic processing times per M-series chip, free alternatives, digitizing MiniDV tapes and DVDs, and a batch weekend workflow.
-
Windsurf: Using write-mode sparingly to protect your muscle memory
A field-tested take on using write-mode sparingly to protect your muscle memory with Windsurf: what it rewards, where it breaks, and how to keep the workflow honest.
-
How to Automate Your Personal Workflow with Python
Learn to automate repetitive tasks with Python. From file organization to email processing, web scraping to data transforms, this practical guide shows.
-
Why AI Will Never Replace Lawyers (And That's Not the Point)
AI is transforming law not by replacing lawyers but by commoditizing routine legal work, creating a barbell profession of high-judgment experts and AI operators.
-
The M-Series Chip Buying Guide for AI — What Actually Matters
Which Mac to buy for local AI and LLMs — M-series memory bandwidth compared (base vs Pro vs Max vs Ultra in GB/s), RAM tiers mapped to model sizes from 8B to 70B+, why the Neural Engine barely matters, and buying advice for students, developers, and AI homelabs.
-
Cursor: Pairing tab with explicit intent comments to steer predictions
A field-tested take on pairing tab with explicit intent comments to steer predictions with Cursor: what it rewards, where it breaks, and how to keep the workflow honest.
-
Monitoring Is More Important Than New Features
New features get applause. Monitoring prevents disasters. Learn why observability deserves more priority than that shiny new feature, and how to build.
