问HN：你目前使用的LLM辅助编码工具是什么？
大家好，我正在测试和比较各种大型语言模型（LLM）辅助的编码工具，想了解一下你们在日常开发工作流程中使用的工具。以下是我一些观察和问题：
1. Cursor 和 Windsurf
- 两者在本地运行良好，但它们使用了节省令牌的策略：
- 在非常长的上下文中，它们可能会截断重要信息，导致建议的代码缺少关键细节。
- 即使在正常情况下，复杂的案例也可能超出上下文或配额限制，从而中断建议。
2. “Roo Code”和基于API的方法
- 直接调用付费API（例如，OpenAI的ChatGPT/GPT-4 API）效果很好，但成本较高。
- 一些免费的或社区的API（开源镜像、社区版）可能不稳定、受限于调用频率或速度较慢。
3. Augment Code
- 据说这是最“智能”的商业产品之一，但价格也很高。
- 许多人推荐它的重写、重构、生成测试等功能，但对于简单的代码补全，其性价比可能低于一些较小的供应商或开源插件。
4. Refact.ai
- 在SWE Bench上排名靠前，声称支持代码重构、通过LLM生成注释、批量重写等功能。
- 然而，它似乎在开发者圈子中很少被讨论。它的支持效果如何？
社区提问：
- 你目前使用的LLM辅助编码工具是什么？（IDE插件、独立客户端或基于API的）
- 选择它的主要原因是什么？（例如，成本、响应速度、上下文长度支持、功能集等）
- 在实际开发中你遇到了哪些优缺点？具体来说，它在调试、重构、生成单元测试、自动修复错误等方面表现如何？
- 如果你之前更换过工具，为什么会更换？
感谢大家分享你们的经验！
查看原文
Hello everyone, I’m testing and comparing various LLM-assisted coding tools, and I want to know which tool you are currently using in your daily development workflow. Here are some observations and questions I have:<p>1. Cursor and Windsurf<p><pre><code> - Both work nicely on local, but they use token-saving strategies:
- With very long context, they may truncate important information, causing the suggested code to miss key details.
- Even in normal scenarios, complex cases might exceed context or quota limits, interrupting suggestions.
</code></pre>
2. “Roo Code” and API-based approaches<p><pre><code> - Directly calling paid APIs (e.g., OpenAI’s ChatGPT/GPT-4 API) works well but is expensive.
- Some free or community APIs (open-source mirrors, community editions) can be unstable, rate-limited, or slow.
</code></pre>
3. Augment Code
- It’s said to be one of the most “intelligent” commercial products, but it’s also costly.<p><pre><code> - Many recommend its ability to rewrite, refactor, generate tests, etc., but for simple code completion, its cost-performance ratio may be lower than some smaller vendors or open-source plugins.
</code></pre>
4. Refact.ai<p><pre><code> - Listed at the top on SWE Bench, it claims to support code refactoring, generating comments via LLMs, batch rewrites, and more.
- However, it seems rarely discussed in developer circles. How well does it support?
</code></pre>
Questions for the community:<p>- Which LLM-assisted coding tool are you currently using? (IDE plugin, standalone client, or API-based)<p>- What are the main reasons for choosing it? (e.g., cost, response speed, context length support, feature set, etc.)<p>- What pros and cons have you encountered during actual development? Specifically, how does it perform for debugging, refactoring, generating unit tests, automatic bug fixes, etc.?<p>- If you have switched tools before, why did you switch?<p>Thank you for sharing your experiences!