News for hackers. Stuff that matters.

forrestbao

forrestbao on Hacker News

Re:Mockingbird: A RAG-Focused LLM on Tuesday July 16, 2024 @08:37PM (#40981606)
This rocks! An LLM tailored for RAG.
Re:Show HN: LlaMaKey – One master key for all cloud LLM/GenAI APIs on Thursday February 15, 2024 @02:47PM (#39387595)
Thank you very much! Appreciate your comment and encouragement.

I conceived this idea while working on a project with multiple people to evaluate multiple LLMs. Too many API keys floating here and there in the code. So I said, what if we could use only one master key for all the APIs and hide the real key from users. Then, LlaMakey was born.

Show HN: LlaMaKey – One master key for all cloud LLM/GenAI APIs

Posted by forrestbao on Thursday February 15, 2024 @06:25AM
from the show-hn dept.

https://github.com/TexteaInc/LlaMasterKey

Key management for multiple users and multiple cloud LLM/GenAI APIs is difficult to be both safe and convenient. Sharing keys among users risks leaking the key and makes it difficult to curb the leakage without interruptions. But assigning one key per user per cloud API results in too many keys to keep track of.Meet LlaMa(ster)Key, the secure and easy solution for API key management: * For...

( Read More... | 2 comments | 3 points | on HN )
Re:Show HN: Open-source model and scorecard for measuring hallucinatio... on Monday November 06, 2023 @04:33PM (#38169336)
A smaller model has less capacity and thus is less prone to overfitting, which is a reason of hallucination. Overfitting means that a model cannot adjust its output based on the input that is unseen during training.