Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Thanks for the pointer.

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.



The only significant bit of preprocessing by the language model is tokenization. You can see how it works here: https://beta.openai.com/tokenizer




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: