-
The Podcast Production Stack That Runs Entirely on One MacBook
A complete AI podcast production workflow on Apple Silicon. Audio Hijack recording, AI voice isolation, Whisper transcription with timestamps, local LLM show notes and chapter markers, with prices and free alternatives for every step.
-
Prompt engineering for code: Structured outputs: JSON schemas that keep agents honest
A field-tested take on structured outputs: JSON schemas that keep agents honest with Prompt engineering for code: what it rewards, where it breaks, and how to keep the workflow honest.
-
The Science of Attention: Why You Use Some Products Every Day and Others Not
Discover the science behind why certain products become daily essentials while others gather dust. Learn the psychological principles that determine.
-
What's Missing From Every AI Safety Conversation (And Why Nobody Wants to Bring It Up)
Doomers and deniers dominate AI safety discourse. Both avoid the key question: who decides what AI optimizes for, and who holds them accountable?
-
I Made My Mac Read Every Contract Before I Sign It
How to review contracts with a local LLM on Mac. PDF to text extraction, a complete structured legal review prompt, context window settings for long documents, and why local AI matters for leases, NDAs, and employment contracts.
-
Cline and Roo Code: Building an internal guardrails library on top of Cline
A field-tested take on building an internal guardrails library on top of Cline with Cline and Roo Code: what it rewards, where it breaks, and how to keep the workflow honest.
-
What Hardware Actually Makes Sense to Buy Today (and What Is Just Marketing)
Cut through marketing hype to discover which hardware purchases actually make sense in 2026. Learn to identify genuine value versus manufactured demand.
-
Japan's AI Strategy Failed in the 1980s. Here's What Europe Should Learn.
Japan's ¥50 billion Fifth Generation Project failed because it bet on the wrong paradigm and couldn't adapt. Europe's AI strategy has the same structural flaws.
-
LM Studio vs. Ollama — The Local AI Showdown Nobody Wrote Honestly
An honest LM Studio vs Ollama comparison on Apple Silicon. MLX vs llama.cpp performance benchmarks, model storage locations, how to share GGUF files between both, and which local AI tool fits developers vs tinkerers.
-
JetBrains AI Assistant: When the IDE already knows the answer and the agent just needs to ask
A field-tested take on when the IDE already knows the answer and the agent just needs to ask with JetBrains AI Assistant: what it rewards, where it breaks, and how to keep the workflow honest.
-
Inside the Blog Automation Stack: The Full Playbook
Premium deep dive: the end-to-end automation stack behind this blog — daily deploy windows, Medium syndication rate limits, search-engine pings, and the guardrails that keep 5,000 pages building in under 45 minutes.
