Mar 31 · 4 min read · A recent essay, "After Two Years of Vibecoding, I'm Mass Deleting My AI Slop", struck a nerve. The author spent two years going deeper into AI-assisted coding — starting with small tasks, eventually handing over entire features. The excitement faded ...
Join discussionMar 31 · 8 min read · You asked an AI to build you an app. It looks good and it works. Almost. The moment you touch one feature, another one breaks. Every time a real user tries it, there's a bug. (No no, don't click that.) The login doesn't actually protect anything. One...
Join discussion
Mar 18 · 7 min read · Every major tech company is pushing AI-generated code. Microsoft says 30% (targeting 80%). Google says 30%. Uber reports 65-72%. Amazon mandated 80% AI tool usage. Shopify made AI "mandatory." But Goo
Join discussionFeb 28 · 11 min read · Not because it was bad code. It compiled. It ran. It even looked clean. But it solved the wrong problem. I’d asked for a Supabase auth flow with row-level security. What I got was a beautiful, production-grade auth system — using Firebase. Claude Cod...
Join discussion
Jan 10 · 8 min read · When I started building Cyber Code Academy, a coding challenge platform where users submit Python code that gets executed on my server, I knew I was playing with fire. Letting strangers run code on your infrastructure is basically an open invitation ...
Join discussion
Dec 18, 2025 · 5 min read · "Vibe coding" has become a popular phrase lately. It's not describing a specific tech stack, but rather a state of development where inspiration flows into working code with minimal friction — smooth as silk. In 2026, the real competitive edge in pr...
Join discussionDec 3, 2025 · 3 min read · 토큰 효율성이란? 토큰 효율성은 AI 코딩 도구를 활용할 때 최소한의 컨텍스트로 최대한 정확한 결과를 얻기 위한 원칙AI가 코드를 이해하고 수정하는 데 필요한 정보를 최적화하여 생산성을 향상가능 토큰 효율성이 필요한 이유 Context Window 한계 AI 모델은 한 번에 처리할 수 있는 토큰 수가 제한됨 (128K, 200K 등) 더 많은 파일을 읽을수록 중요한 정보가 희석됨 집중된 컨텍스트 = 더 정확한 이해 응답 속도 적은 토큰 = ...
Join discussion
