367 points on HN say agentic coding is a trap. I have logs that say something more uncomfortable: sometimes it saves 3 hours, sometimes it sends me down a 4-hour rabbit hole. The difference isn't the agent — it's the contract you sign before you send it to work.
May 04 2026 · 8′ · Opinion · produccion · railway
I took the DeepClaude repo (467 points on HN) and dropped it into my real production loop. The combination isn't simply "better than either alone" — there's a specific task regime where DeepSeek V4 Pro destroys and Claude fails, and vice versa. Here are my actual numbers.
May 04 2026 · 8′ · Experiments · TypeScript · claude code
Specsmaxxing promises to cure "AI psychosis" with YAML specs for agents. I applied it to my real workflow with Claude Code and found the trap nobody mentions: the quality problem doesn't disappear — it moves into the YAML.
May 03 2026 · 8′ · Experiments · Next.js · TypeScript
Spotify's "human artist" badge hit 243 points on HN. This isn't a music industry problem. It's a leading indicator. If music already needs to prove a human made it, code and posts are next — and nobody has the stack to handle it yet.
May 02 2026 · 9′ · Opinion · npm · claude code
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
I ran git blame on a project where I used Claude Code heavily. 61% of the lines aren't mine. That's not a legal problem yet — it's an accountability problem for when something blows up in production and nobody knows whose signature is on it.
Apr 29 2026 · 8′ · Opinion · TypeScript · claude code
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
742 points on HN about Claude Code quality reports. Anthropic published a reassuring update. I opened my logs from the last 90 days and ran the same prompts the community keeps complaining about. The answer wasn't what I expected.
Apr 24 2026 · 8′ · Experiments · TypeScript · claude code
229 points on HN, trending everywhere. I ran Zed's parallel agents against my Claude Code setup and measured where each one wins. Spoiler: parallelization solves the wrong problem if your bottleneck is context, not speed.
Apr 23 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