|
|
|
|
|
by belval
128 days ago
|
|
My pet peeve with AI is that it tends to work better in codebase where humans do well and for the same reason. Large orchestration package without any tests that relies on a bunch of microservices to work? Claude Code will be as confused as our SDEs. This in turns lead to broader effort to refactor our antiquated packages in the name of "making it compatible with AI" which actually means compatible with humans. |
|
Always make it write out a plan, write out unit tests that match the codebase as-is, and if adjusted are only changed in how they call the code in the future, giving you confidence that the rewrite didn't break core logic.