-
The Specific Mechanism by Which LLMs Confabulate (And Why It Can't Be Fixed with More Data)
LLM hallucination is architectural, not a data problem. Understanding why models confabulate determines which interventions work and which are wasted effort.
-
Local AI for Students — The Study System That Beats Tutoring
A complete local AI study system for students: refurbished M1 MacBook with Ollama, Whisper lecture transcription, Feynman-technique prompts, Anki flashcard generation, and an honest take on AI vs human tutoring and academic integrity.
-
ChatGPT Codex: Auditing the diff, not the narrative – the code is the contract
A field-tested take on auditing the diff, not the narrative – the code is the contract with ChatGPT Codex: what it rewards, where it breaks, and how to keep the workflow honest.
-
When Is It Worth Buying a New Generation Product – and When Not at All
Learn when upgrading to new product generations makes financial sense and when keeping your current device is smarter. Practical frameworks for tech.
-
How Privacy Became a Luxury Product (And Who That Hurts Most)
Privacy now costs money — better phones, paid apps, strong privacy law. Those most exposed to surveillance have the least power and resources to resist it.
-
The AI Photography Workflow Pros Run on MacBook Pros
A professional AI photography workflow on MacBook Pro: AI culling tools, Lightroom AI masking and Denoise benchmarks on M-series chips, Topaz and DxO processing times, and where AI must stay out of pro work.
-
Claude Code: Keeping Claude honest with explicit acceptance criteria, not vibes
A field-tested take on keeping Claude honest with explicit acceptance criteria, not vibes with Claude Code: what it rewards, where it breaks, and how to keep the workflow honest.
-
How to Recognize When Technology Has Matured and Isn't Just Hype
Learn the reliable indicators that distinguish mature, adoption-ready technology from hype cycles. Practical frameworks for evaluating when new tech is.
-
What the Newspaper Industry's Death Teaches the Web About Surviving AI
Newspapers misunderstood what they were selling. Web publishers are making the identical mistake with AI — here's the asset that actually survives disruption.
-
Make Siri Actually Smart — The Local LLM Bridge Trick
How to bridge Siri to a local LLM using Apple Shortcuts, Ollama's API, and Tailscale. Voice-query your Mac's AI from your iPhone anywhere, with the exact JSON config and realistic latency numbers.
-
GitHub Copilot: Copilot Spaces as shared context libraries for team onboarding
A field-tested take on Copilot Spaces as shared context libraries for team onboarding with GitHub Copilot: what it rewards, where it breaks, and how to keep the workflow honest.
