October 25th, 2024

Copilot vs. Cursor vs. Cody vs. Supermaven vs. Aider

Vincent Schmalbach prefers Cursor over GitHub Copilot for its effective code modification and autocomplete features, while Aider serves command-line users. Sourcegraph Cody is less reliable for code modifications.

Read original articleLink Icon
Copilot vs. Cursor vs. Cody vs. Supermaven vs. Aider

Vincent Schmalbach compares several AI coding assistants: GitHub Copilot, Cursor, Sourcegraph Cody, Supermaven, and Aider. He transitioned from GitHub Copilot to Cursor in early 2024, finding Cursor's features, particularly the Ctrl+K command for code modifications and the Tab feature for autocomplete, to be more effective for his development work. GitHub Copilot, while revolutionary for its autocomplete capabilities, felt limited as it lacked seamless integration for complex tasks, leading Schmalbach to prefer dedicated chat services for those needs. Cursor's design allows for efficient code editing and real-time suggestions, making it a comprehensive tool for developers. In contrast, Sourcegraph Cody, while feature-rich, does not match Cursor's reliability in code modifications. Schmalbach also highlights the potential of Aider, a command-line tool that facilitates AI-assisted pair programming, emphasizing its focus on terminal-based workflows. He notes that while both Cursor and Aider can modify code effectively, they cater to different user preferences: Cursor for those who favor GUI environments and Aider for command-line enthusiasts. The evolution of these tools reflects a growing trend towards integrating AI into coding practices, enhancing productivity and streamlining workflows.

- Vincent Schmalbach prefers Cursor for its effective code modification and autocomplete features.

- GitHub Copilot, while innovative, lacks the seamless integration needed for complex tasks.

- Sourcegraph Cody offers similar functionality to Cursor but is less reliable in code modifications.

- Aider is a promising command-line tool for AI-assisted pair programming.

- The choice between Cursor and Aider depends on user preference for GUI versus command-line interfaces.

Link Icon 6 comments
By @monatron - 6 months
I'm surprised continue.dev isn't getting a mention here. I've tried copilot, cody, and cursor, and ultimately came back to continue.dev. I can use my own models, api key, etc. The same VSCode setup I'm used to, custom context providers, doc indexing, etc. It's proven to be extremely useful for me - though I use it less for autocomplete, and more for interactive back-and-forth sessions to arrive at a block of code.
By @tonygiorgio - 6 months
Very poor quality and short comparison. Not worth a read.
By @danjl - 6 months
I don't use the autocomplete very often. I do use the chat window to do rubber ducking about potential changes. I ask it about features of the libraries I'm using, the built-in features of the language, ways to restructure the code, various suggested improvements to the algorithms and so forth. After a short discussion about various options, I'll ask you to generate code which I use either as a reference or verbatim. For me rubber ducking and discussions are much more valuable than generating little bits of code using autocomplete.

The next interaction mode I want is to have the AI as a pair programming partner, making comments as I type code, including suggestions and pointing out potential errors, and allowing me to ask questions. That is, similar to the rubber ducking, except that I'd like it to interject comments at the right moments automatically.

By @alexjurkiewicz - 6 months
Copilot was the first mover, but other tools (built on worse models!) can do just as well.

Until one product becomes clearly better, the code AI ecosystem might just churn and churn and churn.

By @mitchitized - 6 months
Wondering why Phind is not more commonly considered, integration with VS Code is stellar, and the quality is pretty good.
By @sidchilling - 6 months
Is there any code assistant that can parse entire big codebases and help me implement a “story”?