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: Almost unusable code generated by ChatGPT recently

6 点作者 illegalmemory超过 1 年前
Lately, I've noticed issues with ChatGPT generating code that is nearly unusable, often leaving massive gaps in the code and prompting me to fill them up. Have you experienced similar outputs?

4 条评论

ipaddr超过 1 年前
This is never reflected in the benchmarks and everyone uses them as imperial universal truths. ChatGPT once reached a certain quality but is scaling down on first requests to save compute power.
verdverm超过 1 年前
There have been several recent HN posts to the same effect. Here&#x27;s a recent one I participated in: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=38602025">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=38602025</a><p>It&#x27;s not limited to ChatGPT either and seems more pervasive. Not sure what&#x27;s happening
评论 #38633317 未加载
runjake超过 1 年前
Data point: it works well here (on a Plus subscription using GPT-4) with Python and JavaScript and Go.<p>I do use highly-tailored starting prompts saved in a GPTs.<p>It&#x27;s definitely gotten a lot slower.
j4hdufd8超过 1 年前
learn to code