From Basics to Agentic RL: A Deep Dive into LLM Tool Use
natolambert · x · 2026-07-31
AI researcher Nathan Lambert shared Lecture 11 of his course, focusing on tool use, function calling, and agent fundamentals.
The lecture systematically covers the underlying principles and infrastructure of LLM tool calls. It also dives into training methods for tool use and cutting-edge challenges in scaling agentic RL, including history, basics, and practical implementations like OpenThoughts-Agent.
Related event: AI Course Details LLM Tool Use and Agent Foundations(2 posts)→
More from coding & agent
- AI Coding Evolution Meme: From Accidental Databases to Neural Networks — sierracatalina · 2026-07-31
- Developer Resumes Year-Long Stalled Game Project Using Claude Opus — CtrlAltDwayne · 2026-07-31
- Infisical Launches Agent Proxy to Prevent AI Agents from Leaking Secrets — ycombinator · 2026-07-31
- Codex Editor Tip: Enable All Statusline Options for Better UX — doodlestein · 2026-07-31
- Developers Praise Cloudflare Agents SDK for Background Sub-Agent Spawning — threepointone · 2026-07-31
- Open-source VS Code extension Antigravity-VSCode connects to Google Antigravity — 3nc0d3d_ · 2026-07-31