Comment by philipwhiuk
3 days ago
> I'm using an LLM to write the code for my current project, but I iterate improvements in the code until it looks like code I wrote myself.
The prevailing research suggests this is not quicker than just writing it in the first place.
It may not be quicker, but it is often more thorough and less stressful on my old joints. It is also far less tiring.
“Take this CSV of survey data and create a web visualization and create a chloropleth map with panning, zooming, and tooltips” I bypass permissions and it’s done in 10 minutes while I go do some laundry. If I did it myself I would not even be done researching a usable library and I would have zero lines of code. Those studies are total nonsense.
I could see it in cases.
LLMs excel at tasks that are fresh. LLMs are wonderful at getting the first 80% of the way there. -- LLMs are phenomenally good for a first draft or so.
I've had worse experiences for getting LLMs / agents to refactor code. I would believe in many cases it could be quicker to just manually go through and make refinements compared to merely getting the LLM to keep trying.
That seems very intuitive to me. If you want extremely specific changes made at extremely specific locations in an extremely specific way then you probably need to do that yourself because a language model can’t read your mind. I think there are very large set of problems where implementation details do not actually matter and cheap, disposable code is not a problem. I don’t think vibecoding is a good idea for missile guidance. Probably OK for a dashboard a manager isn’t really going to use anyway.