But if the audio challenge is not for training and they know the right answer why are you able to pass it by typing something completely different but with some syllables in common? It seems to me either they only have a vague idea of what the right answer is or they are open to the AI being wrong and in future it will be adjusted by input they think is reliable because it’s sort of similar.
But if the audio challenge is not for training and they know the right answer why are you able to pass it by typing something completely different but with some syllables in common? It seems to me either they only have a vague idea of what the right answer is or they are open to the AI being wrong and in future it will be adjusted by input they think is reliable because it’s sort of similar.
Nah they accept a range of inputs because they know different humans can’t consistently produce a single answer.
Maybe if this becomes more popular and gets abused they’ll narrow the range.