---
title: "Cursor"
description: "AI-powered code editor designed to make developers extraordinarily productive through intelligent coding assistance"
---

# Cursor
> AI-powered code editor designed to make developers extraordinarily productive through intelligent coding assistance

## Articles

### [Iterating with shadow workspaces](https://yomu.fyi/post/iterating-with-shadow-workspaces.md)
- Company: [Cursor](https://yomu.fyi/company/cursor.md)
- Author: Arvid Lunnemark
- Published: Sep 1, 2024
- Type: Explainer

Cursor’s shadow workspace addresses the problem of letting AI agents iterate on code without disrupting a developer’s active workspace. The design prioritizes LSP usability—especially lints, definition navigation, and language-server interaction—while also requiring independence, privacy, concurrency, universality, maintainability, and speed. A copied in-memory TextModel was rejected because sharing the user’s language server could introduce copied files into references, duplicate declarations, or miss errors. The implemented approach uses a reusable hidden Electron window for the workspace, routing AI edits through Cursor’s processes and returning lints independently of the visible editor. The post treats runnability as a harder future extension, with folder-proxy designs, platform limitations, and network-level independence still open questions.


### [Series A and Magic](https://yomu.fyi/post/series-a-and-magic.md)
- Company: [Cursor](https://yomu.fyi/company/cursor.md)
- Author: Cursor
- Published: Aug 22, 2024
- Type: Announcement

Cursor announces milestones in its effort to change software development with AI, describing a shift from slow, cumbersome building and modification toward greater lightness and control. The company says its tool replaces searches for primitives with instant answers, turns mechanical refactors into single “tabs,” expands terse directives into working source, and applies thousand-line changes in seconds. It reports more than 40,000 customers and an initial team that has built SOTA next-edit-prediction models, multi-billion-file retrieval systems, and fast code rewrites using speculative inference. The announcement also says Cursor raised $60m in Series A funding from Andreessen Horowitz, Thrive Capital, OpenAI, Jeff Dean, Noam Brown, founders of Stripe, GitHub, Ramp, Perplexity, and OpenAI, and others, while inviting people excited about coding’s future to consider joining the company.


### [More problems](https://yomu.fyi/post/more-problems.md)
- Company: [Cursor](https://yomu.fyi/company/cursor.md)
- Author: Aman Sanger
- Published: May 25, 2024
- Type: Explainer

The post outlines research problems for the next phase of AI programming, centered on making coding systems predict actions, perform larger edits, understand codebases, and debug software. Proposed directions include low-latency next-action models for keystrokes, locations, files, terminal commands, and edits; background execution for “perfect edits” and pseudocode compilation; and multi-file changes supported by stronger tool use, reasoning, and agent trajectories. For context, retrieval alone is described as insufficient for codebase questions requiring multiple hops, while useful context may span documentation, source, history, UI pixels, logs, and messages. The post recommends combining retrieval, recurrence, and long-context attention, alongside specialized rerankers, multi-hop embedders, caching, and codebase-level retrieval. For reliability, it proposes calibrated bug detection, always-on AI linting, runtime-state tracking through cursor/debug, and improved debugger tool use, while noting trade-offs involving latency, false positives, infrastructure, and user experience.


### [Editing Files at 1000 Tokens per Second](https://yomu.fyi/post/editing-files-at-1000-tokens-per-second.md)
- Company: [Cursor](https://yomu.fyi/company/cursor.md)
- Author: Aman Sanger
- Published: May 14, 2024
- Type: Explainer

Large code edits expose coding agents to laziness, inaccuracy, and latency, especially when frontier models must rewrite hundreds of lines. The post presents fast apply, a specialized full-file code-edit model that separates planning from applying: Cursor's frontier model plans the change, while the apply model rewrites the current file. It evaluates roughly 450 edits on files under 400 lines, using Claude-3 Opus as grader, and finds llama-3-70b-ft nearly matches claude-3-opus-diff while outperforming GPT-4-Turbo and GPT-4o. Rather than generate conventional diffs, it uses full-file rewrites and search/replace hunks, which avoid line-number errors and give models more output tokens for reasoning. A custom speculative decoding method, deployed with Fireworks, reaches approximately 1,000 tokens per second on a 70b model, about 13x faster than vanilla Llama-3-70b inference and 9x faster than the previous GPT-4 deployment.


### [Our problems](https://yomu.fyi/post/our-problems.md)
- Company: [Cursor](https://yomu.fyi/company/cursor.md)
- Author: Sualeh Asif
- Published: Oct 12, 2023
- Type: Explainer

The post lays out problems Cursor is working on in AI-assisted coding, from selecting relevant context in large codebases to making edits and finding bugs. It proposes collecting 500k tokens from editor sources and using a custom, fast reranker to reduce that context to 8k tokens, while reporting 1.4 billion vectors and 150,000 codebases indexed as of October 12, 2023. Other planned capabilities include a constrained few-step agent that searches, writes, and runs code with feedback, passive and active bug finding, and larger edits presented in real time. Future ideas include time-warp predictions, code understanding in model weights, reader and pseudo-code modes, and automatic stack-trace fixes. The list is explicitly not a final roadmap because new ideas and priorities change, and the post also invites interested people to join the company.


### [Inference characteristics of Llama](https://yomu.fyi/post/inference-characteristics-of-llama.md)
- Company: [Cursor](https://yomu.fyi/company/cursor.md)
- Author: Aman Sanger
- Published: Jul 20, 2023
- Type: Benchmark

Llama-2-70B is evaluated against GPT-3.5-turbo on serving cost and latency, with the comparison deliberately excluding GPT-4 and noting fine-tuning as a separate reason to choose Llama. The evaluation serves Llama on two 80-GB A100 GPUs in 16-bit precision, then uses transformer FLOP, memory-bandwidth, and KV-cache analysis to explain the difference between prompt processing and token generation. The measurements indicate that Llama-2 has worse completion-token pricing than GPT-3.5 on two A100s, while its prompt-token pricing is more than three times cheaper; eight A100s might improve pricing but introduce unacceptable latency. The resulting guidance favors GPT-3.5 for most workloads and open-source Llama models for prompt-heavy tasks such as classification or reranking, with batch processing and workloads lacking prompt tokens identified as additional cases where Llama may make sense.


### [Prompt design](https://yomu.fyi/post/prompt-design.md)
- Company: [Cursor](https://yomu.fyi/company/cursor.md)
- Author: Arvid Lunnemark
- Published: Jun 11, 2023
- Type: Explainer

The post argues that “prompt design” better describes prompt construction than “prompt engineering,” comparing it with web design. It frames prompts as clear communication with dynamic inputs that must adapt to changing content and context-window limits, then identifies shared practices such as inspecting rendered output, using composable declarative components, and pursuing precise formatting. For LLM agents, the analogy extends to interactive websites whose prompts re-render after function calls, although text-only output and caching constraints differ. This perspective motivates Priompt, a React-like, JSX-based library used internally at Cursor, with a preview site that renders prompts using real request data and serialized props; the author considers JSX more ergonomic than string templates while noting that model capabilities and platform abstractions may weaken the analogy over time.


[Newer posts](https://yomu.fyi/company/cursor/page/6.md)