Comment by worldsayshi 3 months ago Yeah it seems crazy to use LLM on any task where the output can't be easily verified. 1 comment worldsayshi Reply palmotea 3 months ago > Yeah it seems crazy to use LLM on any task where the output can't be easily verified.I disagree, those tasks are perfect for LLMs, since a bug you can't verify isn't a problem when vibecoding.
palmotea 3 months ago > Yeah it seems crazy to use LLM on any task where the output can't be easily verified.I disagree, those tasks are perfect for LLMs, since a bug you can't verify isn't a problem when vibecoding.
> Yeah it seems crazy to use LLM on any task where the output can't be easily verified.
I disagree, those tasks are perfect for LLMs, since a bug you can't verify isn't a problem when vibecoding.