I understand LLMs provide a boost for devs to write code when used as a completion, but I feel it’s a very slippery slope once you start using it, eventually devolving into more work being passed straight through the LLM without much human supervision, so bugs can frequently slip by.
Recently I’ve been annoyed by lower software estability and I’ve seen it starts to drop as soon as an LLM is used heavily for development. Recent example: The newsblur android app, it would crash if I tapped on a subscription group, a paid feature I don’t have but often misclick. Out of curiosity checked their github and lo and behold, main dev has been using Claude for many months.
I understand LLMs provide a boost for devs to write code when used as a completion, but I feel it’s a very slippery slope once you start using it, eventually devolving into more work being passed straight through the LLM without much human supervision, so bugs can frequently slip by.
Recently I’ve been annoyed by lower software estability and I’ve seen it starts to drop as soon as an LLM is used heavily for development. Recent example: The newsblur android app, it would crash if I tapped on a subscription group, a paid feature I don’t have but often misclick. Out of curiosity checked their github and lo and behold, main dev has been using Claude for many months.