Agents Cannot Maintain Systems: The Additive–Transformative Gap in LLM Software Delivery
This article explains why current LLMs cannot safely modify real software
systems, despite impressive code‑generation demos.
Table of contents
The Promise of Automated Software Delivery
In 2026, the automated software delivery dream is for an agent to:
read a repository
understand project structure
plan a multi‑step change
write code, tests, and docs
run the code and fix its own mistakes
produce a PR‑ready diff
The first three tasks are additive; the last three are transformative. The
first thre...
Read more at phroneses.com