George Liu
Subscribe
Sign in
Home
Notes
Claude Plugins
Claude Code
Claude Cowork
Local AI
Archive
About
Latest
Top
Discussions
ChatGPT Codex Flagged My Security Code. Here’s How OpenAI Trusted Access for Cyber Works
OpenAI’s Trusted Access for Cyber program interrupted my Codex session. Five minutes and a driver’s license later, I was back to work
May 5
•
George Liu
2
DeepSeek V4 in Claude Code, Kilo Code, OpenCode: 3-Way AI Verification With GPT-5.5
One API key, three tools, and a skill that runs GPT-5.5, DeepSeek V4 Pro, and Sonnet 4.6 in parallel for second opinions
May 3
•
George Liu
2
2
I Saved $7,189 on Claude Code Tokens. Here’s Every Efficiency Habit That Mattered
220+ sessions, 13,445 turns, four models, five effort levels. Everything ranked by real measured impact.
May 2
•
George Liu
1
Claude Cowork Live Artifacts: First Run With My Claude Code Metrics MCP Server
A live artifact is an HTML page in Claude Cowork. It survives the session and calls your connectors for fresh data every time you open it
May 1
•
George Liu
1
April 2026
I Gave Claude Cowork an Obsidian Second Brain. Here Is What It Remembered After 11 Sessions
Real usage across weeks of drafting, debugging, and content planning was the actual test. The second brain passed some tests and failed others.
Apr 30
•
George Liu
2
My Claude AI Already Remembers Everything. I Built It a Second Brain Anyway.
CLAUDE.md files handle project state. Obsidian handles the knowledge that compounds.
Apr 30
•
George Liu
2
2
Regain Access To Claude Opus 4.6 And Opus 4.5 In Claude Code CLI
Stuck with Opus 4.7 in Claude Code? Get back Opus 4.6 or Opus 4.5 access via /model section
Apr 28
•
George Liu
3
Claude Opus 4.6 vs Opus 4.7 Effort Levels And Prompt Steering Benchmarks
Claude Code benchmarks of 200 headless Claude Code sessions comparing Opus 4.6 and Opus 4.7 1M-context models across effort levels and prompt steering…
Apr 26
•
George Liu
2
1
2
Tested Claude AI LLM Models' Effort Levels - Low To Max: How Claude Opus 4.7 differs
Opus 4.7 [1m], Opus 4.6 [1m], Opus 4.5, and Sonnet 4.6 benchmark tested on 10 prompts at every effort level from low to max
Apr 23
•
George Liu
2
3
I Ran Opus 4.6 and 4.7 on the Same 10 Prompts at 1M Context. The Newer Model Cost 2.17x More
Opus 4.7 [1m] at its shipping xhigh default cost 2.17x Opus 4.6 [1m] at its shipping high default, for +11.1 pp IFEval
Apr 20
•
George Liu
1
2
My Claude Code Plugin Marketplace Is Now Public. Install Session Metrics Skill Plugin
centminmod/claude-plugins is live. One marketplace add, one plugin install, and the session-metrics skill auto-triggers the moment you ask Claude Code…
Apr 18
•
George Liu
1
2
11
I Ran Two Claude Opus 4.7 5hr Sessions In One Day
$100.76 across 763 turns at 98.3% cache hit, and didn't hit any 5-hour limits
Apr 17
•
George Liu
2
2
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
