Tag
Every The Latent Daily story, tool, model and resource tagged “Rlhf”.
The 2022 InstructGPT paper showed that reinforcement learning from human feedback makes models more helpful and less harmful. The method, the results and the trade-offs.
AI Desk4 min read
Proximal Policy Optimization made policy-gradient training simpler and more stable by limiting how far each update can move. How it works and why it is everywhere.
AI Desk3 min read
Why it is hard to make AI systems pursue the goals we actually want, the main techniques used today — from RLHF to constitutional AI — and the open research problems.
AI Desk3 min read
DPO showed language models can be aligned to human preferences without a separate reward model or reinforcement learning. How it works and why it spread so fast.
AI Desk3 min read