News for hackers. Stuff that matters.
Re:GitHub is planning Voice to Code by arez on Thursday November 10, 2022 @04:47AM (#33544298)
one thing that changed that you can see in a demo, that it's speech recognition paired with a neural network. He doesn't have to say "write titanic = titanic.dropDuplicated()" he just says, "drop duplicates from titanic" so you "in theory" have to write less. It probably falls apart when you have more complex things to write and then you have to fallback to speaking it out word for word, but it is an interesting development
Re:GitHub is planning Voice to Code by xigoi on Thursday November 10, 2022 @05:41AM (#33544683)
There is a reason we don't have many programming languages where you can say “drop duplicates from titanic”.
Re:GitHub is planning Voice to Code by tlb on Thursday November 10, 2022 @06:25AM (#33544967)
Programming languages need to be unambiguous, but voice interfaces to them don't have to be. With a voice interface, you can say something vague and see what it gets translated into before and either click Run or edit it.
Re:GitHub is planning Voice to Code by arez on Thursday November 10, 2022 @06:16AM (#33544914)
what's the reason?
Re:GitHub is planning Voice to Code by xigoi on Thursday November 10, 2022 @06:29AM (#33544995)
Natural language is ambiguous and doesn't represent nested structures well.