lol 5000 tests. Agentic code tools have a significant bias to add versus remove/condense. This leads to a lot of bloat and orphaned code. Definitely something that still needs to be solved for by agentic tools.
Ah true, that also can happen — in aggregate I think models will tend to expand codebases versus contract. Though, this is anecdotal and probably is something ai labs and coding agent companies are looking at now.
It’s the same bias for action which makes them code up a change when you genuinely are just asking a question about something. They really want to write code.