adopted ASD-STE100 in my project upon a coworker’s recommendation.
Asking Opus 5 to write comments/commit messages etc in plain English has more benefits than just helping with readability.
It discovers bugs. Critical bugs.😱
I was absolutely gobsmacked after seeing this. Wtf!
- I remember how much effort it took to commit some commands to muscle memory (tcpdump, lsof, nc, openssl, strace etc), and even then just a limited set of these. and now to see agents blaze through a debugging session conjuring commands and spellings I didn’t even know existed 🤯
- In recent weeks, when it came to tricky bugs (a memory leak, a routing issue, a sharding bug), Claude’s initial analysis was almost always 100% wrong. I had to give it multiple hypotheses, clues, ideas, suggestions for it to solve the bug. When asked “so, what did you learn?”
- This is one of all time favorite books on programming, and it goes way harder during this agentic era. My myriad review agents follow many guidelines from this book. The bar for software really should be higher, and it’s sad to see people ship slop.I’ve only read 3 chapters so far but this book is hands down the *best* I’ve read in recent years. Esp this piece on software layering and why “shallow modules” are a trap and the perils of premature, shallow abstractions via small functions/classes (as championed by Clean Code)
- I envy people who, when implementing complex features, have the ability to plan everything down to a T right at the beginning, and know for a fact that it’s the best solution. I’m more of a “pantser”. I discover better ideas as I experiment with code on the fly.

