asoderlind

"What I got wrong was making portability the goal. Portability is insurance."

I was reading this blog post. But then something changed. I realized that what I was reading was not human-written at all -- it was slop.

If the author doesn't care enough to write it, why should I care to read it? Also all I see it people optimizing their setups/harnesses/contexts but no one ever mentions good real-life use-cases.

I think this is overlooking the fact that assigning a coding assistant to fix the bugs it re-introduces for all eternity just leads to spiraling token costs, which might cost more than just hiring a competent engineer in the first place.

Very well written article, joy to read, which is getting more rare these days.

Also I think it's always worth repeating the risk of losing long-term institutional knowledge when opting for AI as an explicit replacement for junior devs. Another tragic case of short-term gains prioritized over long-term success.