I work in a huge code base. Thousands of projects I have never even taken a single look at. At least once a day I run into an issue and all I have to do is point an LLM at it, and it will successfully follow the chains of includes and function calls and accurately find root problems.

It massively boosts my efficiency as just reading the code myself would take days.

Even the utility of too many tests is negative. More upkeep and harder to change the code.

And with LLMs also more context and token usage and cost.

The biggest differentiating factor today is engineers and/or decision maker willing to say no to a certain feature or implementation.

It's too easy to add bloat and complexity that can never go away, and with the tooling we now have a significant portion of engineers are now active risk to the projects they are working on.

I disagree because I use it in a pretty huge codebase and it definitely saves time.

I'm not talking about LLM, of course they save time.

I'm talking about adding code to a code base. After a certain size, it's mostly garbage. I subscribe to the old unix principle and I have yet to seen a reason how LLM has changed it, it in fact became much more important now as a coding agent would happily add any crap to any repository.