Re:ChatGPT in an iOS Shortcut – Worlds Smartest HomeKit Voic...
by tarvaina on Sunday January 22, 2023 @06:41AM
(#34476428)
The only significant bit of preprocessing by the language model is tokenization. You can see how it works here: https://beta.openai.com/tokenizer
Any idea of how clever the wrapper around these things is? For example, would OP’s use case simply get forwarded to the neural network as one single input (string of words) or is there some clever preprocessing going on.