Comment on Coinbase CEO explains why he fired engineers who didn’t try AI immediately
Senal@programming.dev 5 days agoIt’s much faster to check code for correctness than it is to write it in the first place.
In certain circumstances sure, but at any level of complexity, not so much.
At some point it becomes less about code correctness and more about logical correctness, which requires contextual domain understanding.
Want to churn out directory changing python scripts, go nuts.
Want to add business logic that isn’t a single discrete change to an existing system, less likely.
For small things is works OK, it’s less useful the more complex the task.
natecox@programming.dev 3 days ago
It’s funny to me that this is even up for discussion. It’s been a truism for as long as I can remember that reading code is much, much more difficult than writing it.
Senal@programming.dev 3 days ago
Perhaps for the the style or complexity of the code you (and i) are seeing on a regular basis this is true.
I find, for low logical complexity code, it’s less about the difficulty of reading it and more about the speed.
I can read significantly quicker than i can type and if the code isn’t something i need additional time to reason about then spotting issue with existing code can be quicker than me writing the same code out.
Boilerplate code is a good example of this.
Though, as i said, I’ve found the point at which that loses it’s reliable usefulness is relatively low in the complexity scale.
The specific issue i have with people pushing LLM’s as a panacea for boilerplate code is that it’s not declarative and is prone to reasonable looking hallucinations , given enough space.
Even boilerplate in large enough amount can be subject to eccentricities of LLM imagination.