2 HN users recommended this podcast episode2 months2024–2025score 2
Years with an HN recommendation, 2007–2026
HN commenters point to it as the best first-hand account of Cursor's technical internals, straight from its founders.
A Lex Fridman podcast conversation with the four creators of Cursor, the AI-assisted code editor. They discuss how the editor integrates models into programming workflows, including custom completion models and techniques like speculative decoding to speed up applying edits.
“The founders did an episode on Lex Fridman's podcast that covers the technical sides of Cursor far better than I ever could” (HN, 2024)
The founders did an episode on Lex Fridman's podcast that covers the technical sides of Cursor far better than I ever could: [this video] But to summarize, Copilot is an okay ChatGPT wrapper for single line code completion. Cursor is a full IDE with AI baked in natively, with use-case specific models for different tasks, intelligent look-ahead, multi-line completion, etc. If Copilot is a horse, Cursor is a Model T.
Cursor founders explain the technical side of the editor
AI enables new tools & features but in itself is not a product. There's a good essay from Andrew Chen on this topic: Revenge of the GPT Wrappers: Defensibility in a world of commoditized AI models "Network effects are what defended consumer products, in particular, but we will also see moats develop from the same places they came from the past decades: B2B-specific moats (workflow, compliance, security, etc), brand/UX, growth/distribution advantages, proprietary data, etc etc." [1] Also check out the podcast with the team at Cursor/Anysphere for details into how they integrate models into workflows [2] [1] [link] [2] [this video]
Details on how Cursor integrates models into workflows
If you use the Cursor IDE: the folks that wrote it talked about their use of speculative decoding to make "Apply" faster on the Lex Friedman podcast last month. Here it is on YouTube, although you can also find it on Spotify and other podcast platforms: [this video]
Cursor team discuss speculative decoding for faster Apply
On the agent side it's just the UI and LLM wrapper really. But the completion is a completely different custom thing. There's a video of the cursor team on Lex Fridman where they mention a few details [this video]
Cursor team mention details of their custom completion model
Video list and Hacker News comment labels from HackerTube (prompted by @karpathy), released under ODC-By 1.0, built on the open-index/hacker-news archive. Hacker News data is provided by Y Combinator; comments remain the work of their authors. Video titles, channel names and thumbnails belong to their creators and are shown via YouTube. HackerTube Watch is an unofficial edition. Data export of 2026-10-31.
Plays via YouTube's privacy-enhanced embed
5 Hacker News comments
From the HN archive; up to 20 kept per video, favoring different commenters. Recommendations first.
Read more
Citations, criticism and jokes