What have you been working on and AI is replacing you?
Really guys, I have a tough time believing AI is really replacing any serious developer.
It still screws up even simple tasks, and it often takes more time to accurately describe what you want than just writing the code.
And most importantly: it cannot understand complex contexts.
I am working on a corporate product that is essentially a big monolith, with much of the logic being complex because of legal reasons (the product is about real estate), and some bad past design decisions.
The features I am currently working on cannot be vibe-coded, because no AI can understand the context. And I have worked with similar projects in the past -I know that corporate software of monstrous complexity is usual.
The same applies to a caching library I am developing on and off on my spare time: I asked Claude to make some improvements, and it didn't even compile. The result was a disaster.
An actual question, to all of you who 'mourn your craft' and LLMs replacing you: what on earth have you been working on?
Am I the only one who doesn't see LLMs replacing us anywhere soon? Or am I just very lucky? > The features I am currently working on cannot be vibe-coded, because no AI can understand the context. It's always possible to improve understanding and put the context into writing, usually just that no one has. Clean up the variable names and docs and the language models (and other developers!) will understand the context better. This amounts to doubling down on clear technical communications. Another way to say it: LLMs are pattern matching machines. So in a twisted way, I see LLMs driving code quality improvements - if only to make the LLMs more effective. Improve the pattern, improve the pattern matching.