RRaghavan T M·Jun 30RLHF: How ChatGPT Learned What You Actually Want Discover how the three-step RLHF process and reward models taught ChatGPT to provide surprisingly useful answers5 min read·changeofbasis.hashnode.dev
AAni·Oct 22, 2024Designing The Perfect Incentivised System - Part 1Perpetual Incentive System - Understanding the Balance of Rewards and Resourcefulness10 min read·blog.anirudha.dev
EEshan Jairath·May 29, 2023Simple Intro to Reinforcement LearningIn this blog, we delve into the technical theory behind RL, its significance, and why it's necessary. We explore how RL addresses different scenarios.9 min read·eshanjairath.hashnode.dev
SShahul Es·May 8, 2023Reward Modeling for Large language models (with code)Reward modeling combined with reinforcement learning has enabled the widespread application of large language models by aligning models to accepted human values. Reward Modelling and RLHF have been the hottest words in AI alignment since the release ...7 min read·explodinggradients.com