[Paper Review] Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Since I have joined a team which deals with AI and LLMs, I have decided to review a paper in relation to an LLM which deals with reinforcement learning of LLM and how it turns out to be better than the zero-shot learning.
It had been only 3 days in t...
ramieeee.me4 min read