Codex, Opus, Gemini try to build Counter Strike
I
instantdb.com 8
High resonance Write Soon
This article strongly resonates and has clear angles for your perspective
Quick Take
This is exactly the kind of hands-on AI evaluation Brian would find valuable - testing three major models on a complex, multi-step engineering task rather than toy problems. The detailed breakdown of where each model excelled (Claude for frontend polish, Gemini for backend logic) provides actionable intelligence for choosing AI tools in real projects.
Relevant Domains
AI/agents/future of software work Engineering craft/architecture/productivity (secondary) Side projects/automation/earning from skills (tertiary)
Blog Angles
1
"I Tested AI Models on Real Engineering Tasks (Not Toy Examples)"
Thesis
Your Hook
2
"The React useEffect Problem Is Blocking AI (And Humans)"
Thesis
Your Hook
3
"Why I'm Not Retiring My IDE Yet: What AI Still Gets Wrong"
Thesis
Your Hook
4
"The AI Model Hierarchy: When to Use Claude vs Gemini vs GPT"
Thesis
Your Hook
Tags
#ai-agents
#model-comparison
#engineering-productivity
#react-dx
#claude-vs-gemini
#ai-limitations
#developer-tools