AI & machine learning2023 · shared on Hacker News
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human
Explore Training a Helpful and Harmless Assistant with Reinforcement Learning from Human, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Yaaronrelph ·
Show HN: ChatLLaMA – A ChatGPT style chatbot for Facebook's LLaMA
23 points2 comments
Ystale2002 ·
Meta wants its open source AI model to be as capable as OpenAI’s best model
15 points2 comments
Ythrowaway888abc ·
The Poison of (LLMs) Alignment
2 points0 comments
Yawyugan ·
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human
1 points1 comments