Running the OWASP LLM Top 10 as a real audit is a completely different experience than reading it as a checklist. I ran it against my TypeScript agent stack with system prompts, MCP tools, and Cline — and the findings were uncomfortable.
Jun 20 2026 · 9′ · Tutorials · TypeScript · LLM
Two weeks using Cline as an autonomous coding agent on a TypeScript project. What tasks I delegated, where it screwed up, how it compares to Claude Code, and which workflows I'd never hand over to it. Architecture-grade analysis, not hype.
Jun 07 2026 · 11′ · Tutorials · TypeScript · developer tools
Functors, monads, and pipe() can look pristine in small examples, but real Next.js flows with Server Actions and Prisma expose readability, bundle, and onboarding costs worth measuring before adopting the full pattern.
May 09 2026 · 8′ · Experiments · TypeScript · produccion
Three deadlocks in production, all with the same face: the service stopped responding — no error, no panic, no log. What I found while diagnosing them changed how I think about lock design in async Rust.
May 07 2026 · 7′ · Tutorials · produccion · railway
After an autonomous agent nearly wiped my production database, I built a real guardrails layer. Here are the controls, the code, and the logs that saved my skin.
May 07 2026 · 6′ · Experiments · TypeScript · produccion
The hype says Kimi K2.6 beat Claude and GPT-5.5 at coding. I ran it against my own codebase — not cherry-picked HumanEval — and what I found changes the question you should actually be asking.
May 03 2026 · 11′ · Experiments · TypeScript · produccion
The HN thread claimed Claude Code blocked or redirected billing when OpenClaw appeared in Git history. I built a public repo, a reproducible harness, and ran the matrix. On Claude Code 2.1.126, I did not reproduce the block.
May 01 2026 · 5′ · Experiments · TypeScript · claude code
The OpenAI on Amazon Bedrock announcement sounds promising. I simulated moving my real API calls to Bedrock and the cold start numbers, IAM overhead, and actual pricing destroy the value proposition for independent projects. The deal benefits AWS, not the dev.
Apr 29 2026 · 9′ · Experiments · LLM · infraestructura
874 points on HN for 'I cancelled Claude'. Before joining the chorus, I ran my own regression cases against real Claude Code logs. The degradation is real — just not where everyone's complaining about it.
Apr 25 2026 · 8′ · Experiments · TypeScript · claude code
Architecture, real systems, product decisions and technical lessons. Everything reviewed with my own judgment before it ships.
213 articles published