News for hackers. Stuff that matters.
Re:Better and Faster Large Language Models via Multi-Token P... by objektif on Wednesday May 01, 2024 @02:22PM (#40227138)
How many times did you have issues communicating with your spouse because of prompting issues? And how did you resolve it?

Why would you need an extra layer here?

Re:Better and Faster Large Language Models via Multi-Token P... by malnourish on Wednesday May 01, 2024 @04:48PM (#40229209)
Why do PR firms and copy editors exist?
Re:Better and Faster Large Language Models via Multi-Token P... by redblacktree on Thursday May 02, 2024 @12:56PM (#40238433)
I don't understand your comment. I was talking about apps built on LLMs where the prompts aren't given by the users, but the LLM is still an important part of the functionality.
Re:Better and Faster Large Language Models via Multi-Token P... by objektif on Sunday May 05, 2024 @09:47PM (#40270384)
I am trying to say in the very near future LLMs will be smart enough to not necessitate a middle man for prompt experimentation.