There we go - my opinions on "vibe coding" after having actually created a full working app with it - as a senior Software Engineer and Cybersecurity expert.
-
There we go - my opinions on "vibe coding" after having actually created a full working app with it - as a senior Software Engineer and Cybersecurity expert.
-
@primeapple With bad code I mean things like code duplication instead of refactoring into common methods, dead code and common security pitfalls. I agree tools could catch some of it, but mostly it comes from the models producing "junior level output" which isn't very surprising due to how LLMs work.
I'm sure Amazon uses the very best of models and tools - yet they also need senior developers to act as code reviewers to stop bad quality from negatively affecting their uptimes.
I don't think the current LLM paradigm can solve this. We'll need AIs that retrain during usage for that (like our human brains do
-
R relay@relay.infosec.exchange shared this topic
