[marcindulak]

After hearing various similarly sounding opinions about CRUD being easy for LLMs, I started tracking how well LLMs handle a standard CRUD Django app I'm familiar with at https://github.com/marcindulak/learning-api-styles-gen-ai-ex....

So far it appears that LLMs still require constant hand-holding, even for a small educational CRUD app.

[magicalhippo]

We've had reasonable effectiveness for CRUD. It's mainly the UI toolkits we use, but the plumbing it can do quite well. It's not 100% vibecoding but certainly a significant accelerator for parts of the job.