New Lex Fridman Insight: Cursor Team: Future of Programming with AI
Sent May 30, 2026
Key Insights
- Cursor's AI-enhanced code editor is built on VS Code to leverage GitHub Copilot's capabilities.
- Cursor uses a sparse model to efficiently handle long input contexts, reducing GPU load.
- Speculative edits in Cursor speed up code generation by processing multiple tokens at once.
- Homomorphic encryption could allow encrypted input processing without data exposure, but it's currently inefficient.
- Aman predicts a Fields Medal before AGI, estimating the milestone around 2028-2030.
How the conversation moved
The episode begins with a discussion on the evolution of code editors, focusing on the Cursor team's decision to build their AI-enhanced code editor on top of VS Code. This choice was driven by the desire to harness the capabilities of GitHub Copilot, which was only available on VS Code, and to have greater control over integrating AI features. The team believed that the predictable progress in AI capabilities, as indicated by OpenAI's scaling laws papers, would significantly change how software is built, justifying their decision to fork VS Code.
The conversation then moves to the innovative features of Cursor, particularly how it enhances programming efficiency through intelligent code editing and prediction. The team integrates UX design with model training to create a seamless user experience, aiming to eliminate low entropy actions in code editing by predicting the next steps a programmer will take. They employ a sparse model, specifically an MOE, to handle long input contexts efficiently while generating fewer output tokens, thus maintaining low latency and reducing GPU load during tasks.
Despite the enthusiasm for AI-enhanced coding, there was little direct pushback from Lex or the guests on the potential downsides of these technologies. However, Aman did express skepticism about the effectiveness of models in bug detection, noting that they are poorly calibrated even when prompted. This highlights a tension between the potential of AI to transform coding and the current limitations in its application, especially in areas requiring high precision like bug detection and formal verification.
The episode concludes with a forward-looking discussion on the future of programming and AI's role in it. Aman predicts that a Fields Medal might be awarded before achieving AGI, estimating this milestone around 2028-2030. The conversation also touches on the potential of homomorphic encryption for secure data processing, though it remains inefficient. The guests express optimism about the future of programming, suggesting that AI tools will allow for faster iterations and less upfront planning, shifting the focus from typing code to communicating intent.
Surprising moments
In-depth
AI-enhanced coding
- Cursor is built on VS Code to leverage GitHub Copilot.
- Cursor integrates UX design with model training for efficiency.
- Speculative edits speed up code generation by processing multiple tokens.
- Sparse models handle long input contexts efficiently.
Model optimization
- Key-value caching improves prediction accuracy and speed.
- Homomorphic encryption allows secure data processing but is inefficient.
- Multi-query attention reduces memory bandwidth requirements.
Future predictions
- Aman predicts a Fields Medal before AGI, around 2028-2030.
- AI tools will enhance programming by focusing on intent communication.
Notable Quotes
A big part of being fun is being fast a lot of the time. Fast is fun.
Still open
- Lex questioned whether the current limitations in bug detection by AI models could be overcome with better calibration methods.
- The potential for homomorphic encryption to become efficient enough for practical use in AI remains uncertain.