Comment on AI-generated code contains more bugs and errors than human output

<- View Parent
ThirdConsul@lemmy.ml ⁨3⁩ ⁨days⁩ ago

According to OpenAis internal test suite and system card, hallucination rate is about 50% and the newer the model the worse it gets.

And that fact remains unchanged on other LLM models.

source
Sort:hotnewtop