-
Your MacBook Battery Can Handle 8 Hours of Local AI — Here's How
Local AI on MacBook battery power: measured battery drain for 3B, 8B, and 32B LLMs on Apple Silicon, OLLAMA_KEEP_ALIVE tuning, Low Power Mode, and offline AI workflows for flights.
-
Google Gemini: Pairing Gemini with Code Assist for refactors that span a whole module
A field-tested take on pairing Gemini with Code Assist for refactors that span a whole module with Google Gemini: what it rewards, where it breaks, and how to keep the workflow honest.
-
Why Most Product Reviews Have Zero Value for Real Decision Making
Discover why most product reviews fail to help real purchasing decisions. From affiliate bias to context mismatch, learn what makes reviews useless and.
-
The Real Reason Silicon Valley 'Moved Fast and Broke Things' (It Wasn't a Philosophy)
Move fast and break things was never a philosophy — it was a rational strategy for conditions that no longer exist. AI startups still pretend otherwise.
-
The AI Reading Workflow That Lets Me Process 50 Articles a Day
AI reading workflow on Mac: article capture with reader mode, local LLM triage with Ollama, a verbatim summarization prompt template, RSS newsletter filtering, and the honest math behind processing 50 articles daily.
-
ChatGPT Codex: Keeping the human in the loop by requiring explicit acceptance
A field-tested take on keeping the human in the loop by requiring explicit acceptance with ChatGPT Codex: what it rewards, where it breaks, and how to keep the workflow honest.
-
What Happens When We Stop Chasing New Features and Start Optimizing Old Ones
Explore what happens when software teams stop building new features and focus on optimizing existing ones. From reduced bugs to happier users, discover.
-
What IBM Watson's Failure Tells Us About Every AI Hype Cycle That Follows
IBM Watson's collapse cost hundreds of millions and promised to revolutionize medicine. The failure pattern repeating in today's enterprise AI is exact.
-
Run DeepSeek-Class Models on a Mac — The Complete Guide
Complete guide to running DeepSeek-R1 distills and reasoning models on Apple Silicon Macs: distill sizes from 8B to 70B, quantization choices, realistic tokens-per-second by RAM tier, Ollama and LM Studio setup.
-
Claude Code: Hooks that enforce lint, test and security gates before any write
A field-tested take on hooks that enforce lint, test and security gates before any write with Claude Code: what it rewards, where it breaks, and how to keep the workflow honest.
-
The Future of Laptops: Why Performance Is No Longer the Main Selling Point
Explore why laptop buyers no longer prioritize raw performance. From all-day battery life to AI capabilities and seamless ecosystem integration, discover.
