I migrated my entire note stack from Notion to plain Markdown files. The process took three days. What I lost wasn't what I thought I was going to lose — and that tells me something uncomfortable about why I was really using Notion.
Apr 25 2026 · 9′ · Reflections · productividad · workflow
Deezer says 44% of songs uploaded daily are AI-generated. I ran the same exercise on my commits from the last month. The number I found made me feel exactly the same discomfort.
Apr 21 2026 · 8′ · Reflections · TypeScript · productividad
CAPTCHAs were born to prove you're human. Now my agents need to prove they're bots just to function. I measured the retries, the overhead, the real friction. The numbers are ugly.
Apr 20 2026 · 9′ · Reflections · TypeScript · seguridad web
Emacs has spent decades thinking about how to safely grant real system access to unaudited plugins. In 2025, the AI agent ecosystem has the exact same problem — and isn't even having the conversation.
Apr 19 2026 · 8′ · Reflections · seguridad · developer tools
I ran my agents against a test suite I wrote myself and nearly 30% of the passes were technically correct but conceptually hollow. The agent learned to satisfy the assertion, not the problem. That's not a bug in the agent — it's a bug in how I think about tests when I know there's an agent on the ot
Apr 19 2026 · 8′ · Reflections · LLM · agentes-ia
A Hacker News thread with 208 points asks whether AI agent costs grow exponentially. I have months of real production logs. The answer isn't what anyone expects: it's not exponential — it's discrete jumps. And you're the one causing them.
Apr 18 2026 · 7′ · Reflections · TypeScript · optimizacion
Two years of models getting cheaper and smarter every quarter trained us to expect that forever. Opus 4.7 trended today alongside a piece about 'the start of AI scarcity.' I put them together and something clicked. Here's what actually changed.
Apr 17 2026 · 9′ · Reflections · anthropic · LLM
CodeBurn dropped on HN and forced me to calculate my real Claude Code numbers for the first time. The result was uncomfortable: on some tasks I'm burning more tokens debugging the agent than solving the actual problem. That's not a cost issue — it's a design signal.
Apr 17 2026 · 8′ · Reflections · claude code · desarrollo
GitHub has thousands of awesome-* lists but half of them are dead. I built a system that detects the live ones, scrapes them, deduplicates cross-source, and classifies with AI. First of 4 posts documenting the journey.
Apr 17 2026 · 8′ · Reflections
Architecture, real systems, product decisions and technical lessons. Everything reviewed with my own judgment before it ships.
213 articles published