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。

Testing AI/LLMs to see how well they can build a website from scratch

2 点作者 swax大约 1 年前
Wrote an open source command shell wrapper for LLMs to use. Just testing it with with writing a website from scratch. Comparing GPT-4 and Claude 3 Opus. The results: Pretty similar, they can write a PHP page, with components, styles, and active elements like a fun quiz on one of the pages.<p>Video: https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=4TnaJLq0E-o<p>Article: https:&#x2F;&#x2F;naisys.org&#x2F;articles&#x2F;3-dollar-website-gpt4-vs-claude-opus<p>GitHub repo: https:&#x2F;&#x2F;github.com&#x2F;swax&#x2F;NAISYS

1 comment

matt3210大约 1 年前
A real test would be to invent a framework and see if it can do anything on the new framework. Otherwise it’s just a search engine that amalgamates pieces
评论 #39671331 未加载