corpus.blog
41554 blogs · [ { "id": "01a0e2e2-a456-72aa-be60-a812ca7a4b56", "title": "Claude Opus 5 vs Opus 5.5 Effort Levels Benchmark", "url": "https://ai.georgeliu.com/p/claude-opus-5-vs-opus-55-effort-levels", "published_at": "2026-09-25T10:16:14+00:00" }, { "id": "01a08721-918d-708a-9db4-e3e3f229bf8c", "title": "Anthropic Trusted Access For Claude Mythos 5.1 & Fable 5.1", "url": "https://ai.georgeliu.com/p/anthropic-trusted-access-for-claude", "published_at": "2026-09-01T20:28:15+00:00" }, { "id": "01a08721-918d-708a-9db4-e3e3f2799c50", "title": "Claude Sonnet 5 vs Sonnet 4.6 prompt steering benchmark", "url": "https://ai.georgeliu.com/p/claude-sonnet-5-vs-sonnet-46-prompt", "published_at": "2026-08-27T07:26:33+00:00" }, { "id": "01a08721-918d-708a-9db4-e3e3f3766eef", "title": "OpenAI Trusted Access For Cyber's GPT-5.6 Daybreak-Blue Defensive Cyber Security Model", "url": "https://ai.georgeliu.com/p/openai-trusted-access-for-cybers", "published_at": "2026-08-12T12:00:20+00:00" }, { "id": "01a08721-918d-708a-9db4-e3e3f3d423e8", "title": "Claude Opus 4.8 vs Claude Fable 5 benchmark: prompt steering, cost, and latency results", "url": "https://ai.georgeliu.com/p/claude-opus-48-vs-claude-fable-5", "published_at": "2026-06-11T19:47:22+00:00" }, { "id": "01a08721-918d-708a-9db4-e3e3f4b45f04", "title": "ChatGPT Codex Flagged My Security Code. Here’s How OpenAI Trusted Access for Cyber Works", "url": "https://ai.georgeliu.com/p/chatgpt-codex-flagged-my-security", "published_at": "2026-05-05T12:24:32+00:00" }, { "id": "01a08721-918d-708a-9db4-e3e3f52d9507", "title": "DeepSeek V4 in Claude Code, Kilo Code, OpenCode: 3-Way AI Verification With GPT-5.5", "url": "https://ai.georgeliu.com/p/deepseek-v4-in-claude-code-kilo-code", "published_at": "2026-05-03T06:52:47+00:00" }, { "id": "01a08721-918d-708a-9db4-e3e3f6166297", "title": "I Saved $7,189 on Claude Code Tokens. Here’s Every Efficiency Habit That Mattered", "url": "https://ai.georgeliu.com/p/i-saved-7189-on-claude-code-tokens", "published_at": "2026-05-02T04:49:40+00:00" }, { "id": "01a08721-918d-708a-9db4-e3e3f699d80d", "title": "Claude Cowork Live Artifacts: First Run With My Claude Code Metrics MCP Server", "url": "https://ai.georgeliu.com/p/claude-cowork-live-artifacts-first", "published_at": "2026-05-01T14:50:50+00:00" }, { "id": "01a08721-918d-708a-9db4-e3e3f7559e62", "title": "I Gave Claude Cowork an Obsidian Second Brain. Here Is What It Remembered After 11 Sessions", "url": "https://ai.georgeliu.com/p/i-gave-claude-cowork-an-obsidian", "published_at": "2026-04-30T03:41:50+00:00" }, { "id": "01a08721-918d-708a-9db4-e3e3f7f9362b", "title": "My Claude AI Already Remembers Everything. I Built It a Second Brain Anyway.", "url": "https://ai.georgeliu.com/p/my-claude-ai-already-remembers-everything", "published_at": "2026-04-30T03:36:50+00:00" }, { "id": "01a08721-918d-708a-9db4-e3e3f8565217", "title": "Regain Access To Claude Opus 4.6 And Opus 4.5 In Claude Code CLI", "url": "https://ai.georgeliu.com/p/regain-access-to-claude-opus-46-and", "published_at": "2026-04-28T02:45:28+00:00" }, { "id": "01a08721-918d-708a-9db4-e3e3f9259b3b", "title": "Claude Opus 4.6 vs Opus 4.7 Effort Levels And Prompt Steering Benchmarks", "url": "https://ai.georgeliu.com/p/claude-opus-46-vs-opus-47-effort", "published_at": "2026-04-26T08:44:27+00:00" }, { "id": "01a08721-918d-708a-9db4-e3e3f9a88601", "title": "Tested Claude AI LLM Models' Effort Levels - Low To Max: How Claude Opus 4.7 differs", "url": "https://ai.georgeliu.com/p/tested-claude-ai-llm-models-effort", "published_at": "2026-04-23T14:09:06+00:00" }, { "id": "01a08721-918d-708a-9db4-e3e3fa0dfcc6", "title": "I Ran Opus 4.6 and 4.7 on the Same 10 Prompts at 1M Context. The Newer Model Cost 2.17x More", "url": "https://ai.georgeliu.com/p/i-ran-opus-46-and-47-on-the-same", "published_at": "2026-04-20T19:13:59+00:00" }, { "id": "01a08721-918d-708a-9db4-e3e3fa6cb0bc", "title": "My Claude Code Plugin Marketplace Is Now Public. Install Session Metrics Skill Plugin", "url": "https://ai.georgeliu.com/p/my-claude-code-plugin-marketplace", "published_at": "2026-04-18T14:25:04+00:00" }, { "id": "01a08721-918d-708a-9db4-e3e3fa9e6a76", "title": "I Ran Two Claude Opus 4.7 5hr Sessions In One Day", "url": "https://ai.georgeliu.com/p/i-ran-two-claude-opus-47-5hr-sessions", "published_at": "2026-04-17T14:54:29+00:00" }, { "id": "01a08721-918d-708a-9db4-e3e3fb61aad8", "title": "Six Things to Change in Your Claude Code Workflow for Opus 4.7", "url": "https://ai.georgeliu.com/p/six-things-to-change-in-your-claude", "published_at": "2026-04-17T01:38:51+00:00" }, { "id": "01a08721-918d-708a-9db4-e3e3fbf27573", "title": "How I Built Polished Demo Videos With Remotion, Claude Code, and Claude Cowork", "url": "https://ai.georgeliu.com/p/how-i-built-polished-demo-videos", "published_at": "2026-04-16T12:45:41+00:00" }, { "id": "01a08721-918d-708a-9db4-e3e3fcb7117c", "title": "I Built a Token Cost Analyzer Skill for Claude Code. Here’s What I Found", "url": "https://ai.georgeliu.com/p/i-built-a-token-cost-analyzer-skill", "published_at": "2026-04-16T04:20:14+00:00" }, { "id": "01a08721-918d-708a-9db4-e3e3fcdcc658", "title": "Claude AI Desktop App Gets Redesigned", "url": "https://ai.georgeliu.com/p/claude-ai-desktop-app-gets-redesigned", "published_at": "2026-04-15T01:13:53+00:00" } ] posts Claim your blog
Back to George Liu | Substack
Blog · corpus.blog/blogs/ai.georgeliu.com/posts

George Liu | Substack

ai.georgeliu.com

2026

Claude Opus 5 vs Opus 5.5 Effort Levels Benchmarkoriginal ↗
25 Sept 2026
Anthropic Trusted Access For Claude Mythos 5.1 & Fable 5.1original ↗
1 Sept 2026
Claude Sonnet 5 vs Sonnet 4.6 prompt steering benchmarkoriginal ↗
27 Aug 2026
OpenAI Trusted Access For Cyber's GPT-5.6 Daybreak-Blue Defensive Cyber Security Modeloriginal ↗
12 Aug 2026
Claude Opus 4.8 vs Claude Fable 5 benchmark: prompt steering, cost, and latency resultsoriginal ↗
11 Jun 2026
ChatGPT Codex Flagged My Security Code. Here’s How OpenAI Trusted Access for Cyber Worksoriginal ↗
5 May 2026
DeepSeek V4 in Claude Code, Kilo Code, OpenCode: 3-Way AI Verification With GPT-5.5original ↗
3 May 2026
I Saved $7,189 on Claude Code Tokens. Here’s Every Efficiency Habit That Matteredoriginal ↗
2 May 2026
Claude Cowork Live Artifacts: First Run With My Claude Code Metrics MCP Serveroriginal ↗
1 May 2026
I Gave Claude Cowork an Obsidian Second Brain. Here Is What It Remembered After 11 Sessionsoriginal ↗
30 Apr 2026
My Claude AI Already Remembers Everything. I Built It a Second Brain Anyway.original ↗
30 Apr 2026
Regain Access To Claude Opus 4.6 And Opus 4.5 In Claude Code CLIoriginal ↗
28 Apr 2026
Claude Opus 4.6 vs Opus 4.7 Effort Levels And Prompt Steering Benchmarksoriginal ↗
26 Apr 2026
Tested Claude AI LLM Models' Effort Levels - Low To Max: How Claude Opus 4.7 differsoriginal ↗
23 Apr 2026
I Ran Opus 4.6 and 4.7 on the Same 10 Prompts at 1M Context. The Newer Model Cost 2.17x Moreoriginal ↗
20 Apr 2026
My Claude Code Plugin Marketplace Is Now Public. Install Session Metrics Skill Pluginoriginal ↗
18 Apr 2026
I Ran Two Claude Opus 4.7 5hr Sessions In One Dayoriginal ↗
17 Apr 2026
Six Things to Change in Your Claude Code Workflow for Opus 4.7original ↗
17 Apr 2026
How I Built Polished Demo Videos With Remotion, Claude Code, and Claude Coworkoriginal ↗
16 Apr 2026
I Built a Token Cost Analyzer Skill for Claude Code. Here’s What I Foundoriginal ↗
16 Apr 2026
Claude AI Desktop App Gets Redesignedoriginal ↗
15 Apr 2026