George Liu
CentminMod maintainer, Cloudflare MVP; posts deep‑dive threads on OpenTelemetry, Grafana, AI tool instrumentation, and observability metrics for performance and reliability.
Claude Nails My Reference Style with AI Art
Loving my AI image creator skill. Claude generated this image perfectly based on my reference style 😍
Cross‑sandbox Session Logs Now Searchable with Claude Cowork
Testing my new Claude Cowork Project Sessions MCP server and Skill bundle allows me to backup, search, read, and list other project session logs even if they are in isolated sandboxes 🤓 It allows Claude Cowork projects to read other...
Smaller Context Window Runs Faster, Larger One Slower
Google Gemma 4 26B-A4B ran on MacBoook Pro M4 Pro 48GB ram with competing apps using memory ran at ~56 tokens/second & 48K token context window max memory limited on LM Studio. Compared to ~18 tokens/second higher 64K token context...
Claude Desktop Now Bridges to GPT‑5.4 via Codex CLI
Add an OpenAI Codex GPT-5.4 CLI MCP bridge server to my Claude Desktop MacOS app to allow Claude Desktop & Claude Cowork to talk with GPT-5.4 even within Cowork's sandboxed environment 🤓 Used Codex MacOS app to build the Codex...
Optimizing AI Usage by Scheduling Off-Peak Hours
With Anthropic's new reduced Claude peak hour usage limits, I'm scheduling my Claude Code/Cowork usage with Claude Opus/Sonnet off-peak Brisbane 5AM start and for peak times, using OpenAI Codex CLI GPT-5 now 🤓 Using my Timezones Scheduler app to make...
Claude Cowork Streamlines Project Planning and Content Creation
Been using Claude Code for ages but decided to try Claude Cowork on MacOS desktop app & setup Claude Cowork project to organise/plan my new Subtack I created https://ai.georgeliu.com. So draft posts, image assets all generated within project & even...
Run Google Gemma 4 Locally with LM Studio & CLI
More local AI testing with Google Gemma 4 26B-A4B via LM Studio desktop app and also via headless CLI and using Claude Code https://ai.georgeliu.com/p/running-google-gemma-4-locally-with 🤓
New AI Image Creator Supports Claude & Multiple Models
Updated my AI Image Creator skill to support both Claude Code & Claude Desktop & Claude Cowork. You can now ask Claude to generate images via Google Gemini 3.1 Image Flash (Google Nano Banana 2), Flux 2, Riverflow 2 Pro,...
Google AI Pro Doubles Storage to 5 TB
So my Google AI Pro $20/plan got a storage upgrade from 2TB to 5TB 😎 https://9to5google.com/2026/04/01/google-ai-pro-5-tb/
FirePass Unlocks Unlimited Kimi K2 Turbo for $7/Week
FireworksAI has released FirePass subscription to access Kimi K2 Turbo - a faster Kimi K2.5 serverless API $7/week unlimited tokens with first week free for use with agentic coding harnesses like OpenCode, Cline, Roo Code, Kilo Code, and OpenClaw...
96GB VRAM Setup: 4× Intel ARC Pro B60 GPUs
96GB VRAM - 4x 24GB Intel ARC Pro B60 GPUs for local AI LLMs https://www.youtube.com/watch?v=-aEHitayNts 🤓
Claude Code Flags Dependabot PRs that May Break Cloudflare Workers
Claude Code giving useful reminders for GitHub workflow dependabot PR recommendations that may break my app's usage on Cloudflare Workers platform 🤓 👍
Custom AI Bot Built on Cloudflare May Be Costly
Created my own custom AI chat bot trained on my site data using Cloudflare AI Search/Workers and Cloudflare AI Gateway which has firewall, Guardrails option feature. Seems could be quite expensive to enable 🤔
Latest AI Models Clash: Performance Showdown
AI comparison test: GPT-5.4 vs Claude 4.6 vs Gemini 3.1 Pro vs Grok 4.20 https://www.youtube.com/watch?v=kmiAGfGbjlo
Tracking Claude Code Performance with OpenTelemetry and Grafana
On a roll with Claude Code with Claude Opus/Sonnet and GLM-5 with my Claude Code OpenTelemetry Grafana usage metrics 🤓
