How Claude Code Rewrote Software — Lenny's Podcast (Boris Cherny)
Streams straight from the publisher. podnod never proxies or re-hosts episode audio.
Claude Code has become a co‑worker: Boris Cherny explains how 100% of his code is now AI‑authored and engineers ship dozens of PRs a day. This condensed summary (1 hour → 6 minutes) from Lenny Rachitsky's interview with Boris Cherny covers the rise of agentic coding, product lessons, and safety tradeoffs. You'll learn why starting in the terminal accelerated iteration, how Anthropic layers mechanistic interpretability, lab evals, and real‑world use to manage AI alignment and ethics, and why Boris recommends building for the model you’ll have next—favoring capable models, plan mode, and generous token experiments. Topics include artificial intelligence and machine learning, agent platforms, startups and product strategy, and the economics of developer productivity (Boris cites ~200% gains). Hosts: Lenny Rachitsky; Guest: Boris Cherny. Listen now to get the key ideas in minutes.
No links were found in this episode’s notes.