Comment by rednafi
21 days ago
Everyone claims they are x% more productive with LLMs, but once a greenfield project turns into a brownfield one, the second law of thermodynamics kicks in and these disposable components start becoming a liability.
On top of that, Hyrum’s law doesn’t go away just because your software has explicit contracts. In my experience, as more people start losing their agency over the code they generate, the system accumulates implicit cruft over time and other code starts depending on it.
Also, reliability is a reasoning problem. So operational excellence becomes scrappy with this way of working. It works for some software, but I don’t know whether this push to YOLO it is actually a good thing. C-levels are putting immense pressure in many big companies for everyone to adopt these tools and magically increase productivity while decreasing headcount to please investors. Not going too well so far.
A good interface doesn’t magically make vibe-coded implementations with little oversight usable. Rewriting it over and over again in the same manner and expecting improvement is not the kind of engineering I want to do.
> Rewriting it over and over again in the same manner and expecting improvement is not the kind of engineering I want to do.
let's step back a bit and see this from a single system perspective.
you are already doing it (optimizing a function, a hot code path, etc...) over and over again. albeit much slower than an agent can iterate.
Typically, it's not reiterating in the SAME manner. Refactoring happens in the presense of new information. In the case of an agent, that's usually not true.
One can argue that it can be that way if you hook the agent to github/gitlab or jira.