Routing Between Local Gemma and Cloud Gemini 3.5 Flash by How Easily You Can Verify the Output
When I split local and cloud work by whether it was sensitive, or by which was faster, my decisions wobbled every time. The axis that finally held was different: if the output is wrong, can I catch it cheaply and undo it cheaply? Here is a router that chooses a model from verifiability and recovery cost, with working code and a measurement ledger.
When an Overnight Local Agent Crawls by Dawn — Keeping Ollama's Latency Flat by Working Backward from Context Length
Why each step of a long-running local agent gets heavier toward the end, how to measure it from Ollama's timing fields, and how a fixed num_ctx plus a rolling summary keep per-step latency flat.
Pairing a Local LLM With Antigravity to Keep Sensitive Code Off the Cloud
Should you really let a cloud agent read code that holds your billing keys and revenue logic? For indie developers that worry is concrete. Here I pair Ollama and Gemma as a local LLM with Antigravity, routing sensitive parts to local and general parts to the cloud, with the decision rules and measurements.
Parallel Agents Quietly Burn Through Your Quota — A Self-Defense Circuit Breaker When Limits Are Invisible
Even on AI Ultra's high ceiling, running parallel agents can exhaust your allowance without warning and leave later runs half-failing. Assuming the limit is invisible from outside, here is a circuit breaker that records consumption on your side and applies the brakes, drawn from real operation.
Running 50+ AdMob Mediation Groups With Agents — What I Hand Over and What I Keep
Two wallpaper apps on iOS and Android (50M+ downloads in total) put me past 50 AdMob mediation groups. After a month of pushing parts of the workflow onto an agent, here's where it pays off, where I refused to hand over the steering wheel, and the operating templates I now use.
What You Lose When You Treat Antigravity as a Subordinate — A Decade of Solo Dev Perspective
Over-delegating to Antigravity quietly erodes your problem-solving ability. From 10+ years of solo app development, here's how to prevent cognitive outsourcing and keep your developer judgment sharp.
Three Months Using Antigravity as a Creative Assistant: An Artist's Honest Review
An indie creator who develops apps while maintaining an international art practice shares an honest, three-month account of using Antigravity for the work that surrounds creation. What can you delegate? What must stay in your own hands? Here's the dividing line I found.
Gemma 4 Implicit Caching in Antigravity: Cut Your Credit Costs by 40% Without Changing a Line of Code
A practical guide to leveraging Gemma 4's Implicit Caching in Antigravity. Learn how to structure your projects to dramatically reduce credit consumption when working with large codebases.
Fixing Hugging Face Transformers Errors — Identifying the Cause and Resolving It
Hugging Face Transformers errors sorted by symptom: ImportError, CUDA OOM, bf16 on unsupported GPUs, gated-model 401s, and cache bloat. How to identify the cause and work through the fix.
How to Fix Zapier, Make & n8n AI Integration Errors: Auth, Timeouts, and Rate Limits
AI integrations breaking in Zapier, Make, or n8n? This guide covers the root causes of auth errors, timeouts, and rate limits — with step-by-step fixes for each scenario.
Complete AI Design Automation Strategy: Combining Stitch, Figma Make, and MCP
Advanced implementation guide for AI design automation targeting solo developers and small teams. Covers Design.md architecture, Figma Make strategies, MCP code generation, team patterns, and ROI optimization techniques.
Design Judgment in Code: Beyond AI-Generated UI — Practical Techniques for Embedding Intent into Types, Tokens, and Conditionals
Master the comprehensive techniques for embedding human design judgment into code. From TypeScript's type system for expressing UI intent, through strategic design token architecture, to semantic conditional branching and component API patterns. Learn how to inject judgment into AI-generated code and build design systems that reason like humans.