Notion Engineer Geoffrey Litt: Coding Agents Make Coding Lonelier as Understanding Becomes the Bottleneck
Diyi_Yang · x · 2026-09-19
Podcast episode 7, "Software With Taste," features Notion design engineer Geoffrey Litt on how AI coding is outpacing human comprehension.
- Core thesis: "understanding is the new bottleneck" — developers must keep a clear mental model of the project to stay full creative participants; optimizing for speed at the expense of understanding is dangerous
- He shares a practice: using AI to quiz himself during code reviews to check his own comprehension
- He argues coding agents make coding more lonely and wants development made inherently collaborative
- Also covers malleable software, design beyond animation, and cultivating taste
Related event: Notion engineer: understanding is the new bottleneck in AI era(3 posts)→
More from coding & agent
- OpenAI DevDay demo shows forking agent task history at any step — paw_lean · 2026-11-04
- Veteran game dev: "AI builds a full game in a day" posts are mostly hype — bendee983 · 2026-11-04
- Dev builds interactive Excel-to-dashboard with ChatGPT, shares the prompt — TermRemarkable665 · 2026-11-04
- Agents cut dev time from weeks to a day; bottleneck moved to specs and review — Suspicious_Orchid770 · 2026-11-04
- Orgo, a YC-backed platform giving AI agents their own cloud desktops, claims 1,000+ teams — Scobleizer · 2026-11-04
- Founder: Vibe-coded a PMF-successful product, then hired pro devs to fix the mess — sujingshen · 2026-11-04