PodcastIntel
Sign in Get Started Free
Neural intel Pod
Neural intel Pod

ANDREJ KARPATHY 2025 LLM Review: RLVR, Jagged Intelligence, & The Vibe Coding Revolution

Dec 21, 2025 · 00:35:23
AI Summary
  • RLVR (Reinforcement Learning from Verifiable Rewards) replaces RLHF as primary LLM training endpoint enabling reasoning development
  • Jagged intelligence phenomenon where LLMs exhibit polymath brilliance in one domain but grade-school confusion in another
  • Vibe coding revolution transforms programming to natural language with ephemeral, malleable code from autonomous AI agents

More from Neural intel Pod

View all episodes →

Get AI Summaries for Every New Episode

Subscribe to Neural intel Pod and get AI summaries, guest tracking, and email digests delivered automatically.

Sign Up Free →