Taste Skill Review: Anti-Slop Frontend Skill for AI
Taste Skill injects opinionated design rules into Cursor, Claude Code, and Codex to stop AI from generating generic UI slop. Install, config, and honest review.
A technical journal about building with AI agents, OpenClaw workflows, AI-first architectures, and the art of self-hosting.
Written by humans. Optimized for AI discovery.
Recent Posts
LiteRT-LM: Google's Framework for Running LLMs on Edge Devices
Google's open-source LiteRT-LM runs Gemma 4, Llama, Phi-4, and Qwen on phones, Raspberry Pi, and browsers. Powers Chrome, Pixel Watch, Chromebook. One command to try.
Claw Code Review: Open-Source Claude Code Alternative
Claw Code is an open-source clean-room rewrite of Claude Code's agent harness. 72K GitHub stars in days. Python + Rust. Honest review and setup guide.
oh-my-claudecode Review: Multi-Agent for Claude Code
oh-my-claudecode turns Claude Code into a team of AI agents. 3-5x faster, 30-50% cheaper. Zero-config setup. Honest review with setup guide.
Ollama 0.19 MLX Review: 2x Faster on Apple Silicon
Ollama 0.19 switches to Apple's MLX framework for up to 2x faster local LLM inference on Mac. Benchmarks, setup guide, and what it means for local AI.
Quick AI Answers
Direct answers to the most-asked AI questions. Updated daily.
GPT-5.5 (Spud) vs Llama 5 vs Claude Opus 4.6: What We Know Llama 5 vs Claude Opus 4.6 for Coding (April 2026) Llama 5 vs DeepSeek V4: Open-Source Frontier Battle 2026 Llama 5 vs Gemini 3.1 Pro (April 2026 Comparison) Best Open-Source AI Models April 2026: Top 6 Ranked Best Open-Source AI Coding Agents April 2026 Best Speech-to-Text Models April 2026: Top 6 Ranked Best AI Coding Assistants April 2026: Top 7 Ranked How to Run Llama 5 Locally (April 2026 Guide) How to Use Microsoft MAI Models on Foundry (2026)