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.
Why Hacker News points people here: HN commenters point to it as the best first-hand account of Cursor's technical internals, straight from its founders.
“The founders did an episode on Lex Fridman's podcast that covers the technical sides of Cursor far better than I ever could”HN comment, 2024
“The founders did an episode on Lex Fridman's podcast that covers the technical sides of Cursor far better than I ever could”
Cursor founders explain the technical side of the editor
Full comment
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.
Recommendslight_triadFeb 2025
“Also check out the podcast with the team at Cursor/Anysphere for details into how they integrate models into workflows”
Details on how Cursor integrates models into workflows
Full comment
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
Cites itviraptorOct 2024
“Cursor people talked about effectively streaming in and other ideas.”
Cursor team discuss streaming and related ideas
Full comment
That's the basic part. Cursor people talked about effectively streaming in and other ideas. See this video
Cites itcbhlNov 2024
“the folks that wrote it talked about their use of speculative decoding to make "Apply" faster”
Cursor team discuss speculative decoding for faster Apply
Full comment
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
Cites itviraptorApr 2025
“There's a video of the cursor team on Lex Fridman where they mention a few details”
Cursor team mention details of their custom completion model
Full comment
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
