TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Ask HN: Is anyone successfully integrating LLMs with their entire codebase?

5 点作者 roddylindsay10 个月前
My team is using tools like Copilot, Phind and Coderabbit, but these seem mostly useful for code suggestions and feedback related to individual files.<p>Is anyone successfully using tools which, via large context windows&#x2F;RAG&#x2F;other IR techniques, are able to generate or review code with complex dependencies across many different files and code areas (i.e. db, backend, API, frontend)? Or is this still a ways out?

1 comment

wizzard010 个月前
Aider is one tool which works on medium sized repos for me. Make sure to use claude3.5-sonnet or gpt4o, other LLMs are not yet up to the task with the context size required
评论 #40970940 未加载