Reinforcement Learning from Human Feedback—Now in print! Alignment and post-training of LLMs
After ChatGPT used RLHF to become production-ready, this foundational technique exploded in popularity. In this guide, AI expert Nathan Lambert gives a true industry insider's perspective on modern RLHF training pipelines, and their trade-offs. Using hands-on experiments and mini-implementations, Nathan clearly and concisely introduces the alignment techniques that can transform a generic base model into a human-friendly tool. [Read more]
Architecting for Autonomy—New MEAP! Agnostic AI in the enterprise
Deliver the architecture, updating, adapting, and rebuilding your existing systems so that autonomous AI agents can operate safely, responsibly, and at production scale. This book introduces authors Anjali Jain and Philip O'Shaughnessy’s Agentic Enterprise Framework: a domain-agnostic toolkit of patterns, playbooks, and reference models that you can apply to make almost any architecture ready for autonomous agents. [Read more] 4 chapters of this MEAP are available now, with more to follow soon!
|