A Cursor user found that the AI coding assistant suggested they learn to code instead of relying on it to generate code, especially for larger projects. Cursor reportedly set a soft limit of around 800 lines of code, after which it encourages users to break down the problem into smaller, manageable components and code them individually. This implies that while Cursor is a powerful tool for generating code snippets and assisting with smaller tasks, it's not intended to replace the need for coding knowledge, particularly for complex projects. The user's experience highlights the importance of understanding fundamental programming concepts even when using AI coding tools, as they are best utilized as aids in the coding process rather than complete substitutes for a programmer.
A user on the Cursor forum initiated a discussion titled "Cursor told me I should learn coding instead of asking it to generate it (limit of 800 LOCs)." The post details the user's experience encountering a limitation within the Cursor code generation tool. Specifically, when attempting to generate a substantial amount of code, estimated to be around 800 lines of code (LOC), Cursor presented a message advising the user to learn coding instead of relying solely on the tool for such a large task.
The user expresses surprise at this response, particularly because they perceived the task as relatively straightforward, involving the creation of numerous similar functions. They were under the impression that a code generation tool like Cursor would be well-suited for automating this type of repetitive coding task, thereby saving significant time and effort. The user questions why Cursor wouldn't facilitate this process, especially considering the perceived simplicity of generating numerous functions following a consistent pattern.
Furthermore, the user elaborates on the specific task, explaining that it involves generating multiple getter and setter functions within a class. They emphasize the repetitive nature of this task, highlighting the minimal variation between each generated function. This reinforces their belief that code generation should be an ideal solution for this scenario. The user explicitly contrasts the perceived simplicity of iteratively generating these functions with the comparatively greater complexity of learning to code from scratch, implying the latter appears unnecessarily demanding for this specific task.
The post implicitly raises questions about the practical boundaries of code generation tools and when it becomes more beneficial to invest time in manual coding versus leveraging automation. It also touches upon the expectations users might have regarding the capabilities of AI-powered coding assistants and the potential disconnect between those expectations and the current realities of these tools. The user seems to be seeking clarification on the intended use cases for Cursor and exploring the limitations of relying on code generation for larger or more repetitive coding projects.
Summary of Comments ( 315 )
https://news.ycombinator.com/item?id=43351137
Hacker News users largely found the Cursor AI's suggestion to learn coding instead of relying on it for generating large amounts of code (800+ lines of code) reasonable. Several commenters pointed out that understanding the code generated by AI tools is crucial for debugging, maintenance, and integration. Others emphasized the importance of learning fundamental programming concepts regardless of AI assistance, arguing that it's essential for effectively using these tools and understanding their limitations. Some saw the AI's response as a clever way to avoid generating potentially buggy or inefficient code, effectively managing expectations. A few users expressed skepticism about Cursor AI's capabilities if it couldn't handle such a request. Overall, the consensus was that while AI can be a useful coding tool, it shouldn't replace foundational programming knowledge.
The Hacker News post titled "Cursor told me I should learn coding instead of asking it to generate it" has a moderate number of comments discussing the implications of the linked Cursor forum post. The discussion revolves around the limitations of AI coding tools and the importance of understanding code generation rather than blindly relying on it.
Several commenters agree with Cursor's advice. They emphasize that relying solely on AI for code generation without understanding the underlying principles can lead to issues with debugging, maintenance, and adapting the code to evolving needs. One commenter argues that truly understanding programming empowers developers to use AI tools more effectively, directing them towards specific tasks and refining the generated output. Another points out the potential dangers of blindly trusting AI-generated code, especially in situations where security or reliability is critical.
Some commenters question the practicality of Cursor's advice in certain scenarios. They propose that for rapid prototyping or generating boilerplate code, AI tools can be highly beneficial, even if the user doesn't fully grasp the intricacies of the generated code. One commenter mentions that expecting everyone to become proficient coders is unrealistic, especially for individuals focused on other domains who simply need functional code for specific tasks. They suggest that AI can bridge this gap, allowing non-programmers to achieve their goals without extensive coding knowledge.
A few commenters delve into the limitations of current AI technology, arguing that the 800 LOC limit mentioned in the original post highlights the immaturity of these tools. They believe that as AI evolves, the ability to generate larger and more complex codebases will improve, potentially making the advice to learn coding less relevant in certain contexts. However, another commenter counters this argument, pointing out that understanding the underlying logic will always be crucial, regardless of the size of the codebase.
The discussion also touches upon the potential impact of AI coding tools on the software development landscape. Some commenters express concern about the possibility of these tools displacing programmers, while others argue that they will augment developers' capabilities, allowing them to focus on higher-level tasks and problem-solving.
Overall, the comments reflect a nuanced perspective on the role of AI in coding. While acknowledging the potential benefits of AI tools, many commenters stress the ongoing importance of coding knowledge for effective and responsible software development.