News for hackers. Stuff that matters.
Re:LaVague: Open-source Large Action Model to automate Selen... by DanyWin on Wednesday March 13, 2024 @09:25PM (#39699670)
You are exactly right! As I wanted to have a solution that works with many LLMs out of the box, I focused on chain of thoughts and few shot learnings.

Lots of paper show that fine-tuning only helps with steerability and form (https://arxiv.org/abs/2402.05119), therefore I thought it would be sufficient to provide just the right examples and it did work!

We do intend to create a decentralized dataset to further train models and have maybe a 2b or 7b model working well

Re:LaVague: Open-source Large Action Model to automate Selen... by valine on Thursday March 14, 2024 @12:05AM (#39700511)
What kind of problems are you seeing that you think can be improved with a fine tune?
Re:LaVague: Open-source Large Action Model to automate Selen... by msp26 on Thursday March 14, 2024 @07:05AM (#39702380)
Thank you for linking that paper!