Comment on AI agents wrong ~70% of time: Carnegie Mellon study

<- View Parent
zbyte64@awful.systems ⁨2⁩ ⁨days⁩ ago

When LLMs get it right it’s because they’re summarizing a stack overflow or GitHub snippet it was trained on. But you loose all the benefits of other humans commenting on the context, pitfalls and other alternatives.

source
Sort:hotnewtop