alt Hacker NewsNot exactly. It depends how software is written and if there is ADRs in the project. I had to work on projects where there was bugs because someone coded business rules in a very bad and unclear way. You move an if somewhere and something breaks somewhere else. You ask « is this condition the way it’s supposed to work or is it a bug » when software is not clear enough - and often it isn’t because we have to go fast - we ask people to confirm the rule. My point is this, amazingly written software surely works best with LLMs. That’s not the most software written for now because businesses value speed over engineering sometimes (or it’s lack of skills)
Right: software is not necessarily a sufficiently-clear specification, but a sufficiently-clear specification would be software – and you've correctly identified that a good part of your job is ensuring the software provides a sufficiently-clear specification.
Amazingly-written software is necessary for LLMs to work well, but it isn't sufficient: LLMs tend to make nonsensical changes that, while technically implementing what they're asked to do (much of the time), reduce the quality of the software. As this repeats, the LLMs become less and less able to modify the program. This is because they can't program: they can translate, plagiarise, and interpolate, but they're missing several key programming skills, and probably cannot learn them.