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。

Guiding an LLM for Robust Java ByteBuffer Code

2 点作者 mfiguiere23 天前

1 comment

thisdougb23 天前
This reads like mentoring a junior dev. You do mentoring because the pay off is a junior that develops into a senior; writes better code more efficiently. But what&#x27;s the pay off with going through this process with AI?<p>A few days ago I spent an hour trying to get Claude to write unit tests for a relatively simple function, without getting anything functional in return. It produced good (but changing) plans of work, but the code generated didn&#x27;t match the plan (syntax or semantics).<p>Are people simply replacing &#x27;time spent coding&#x27; with &#x27;time spent mentoring AI&#x27;? And is that a useful trade off, given AI forgets everything?<p>I&#x27;d love to see a more honest discussion about the overhead of coding with AI assistance. It&#x27;s still too high an overhead for me at the present capability.
评论 #43717858 未加载