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。

Show HN: I built an open-source “unit testing” suite for prompts ⮂ inputs

5 点作者 jordanf将近 2 年前
Hi HN,<p>I&#x27;m pleased to share Promptspot, an open-source (Apache License 2.0) project that helps automate testing of large language model (LLM) prompts against an array of input data.<p>Modern LLMs offer an enormous amount of leverage if you &quot;teach the bot to fish&quot; — i.e. simply prompt it with both a &quot;system prompt&quot; (which typically doesn&#x27;t change often) and a dynamic input, which is often application state, search results, recent activity, user profile data, etc.<p>Existing playgrounds and prompt management systems often lack the rigor and flexibility required for this dynamic approach — and as more teams adopt this pattern, I hope Promptspot can become a useful tool for testing, monitoring, and centralizing this data.<p>Promptspot currently supports text-davinci-003 from OpenAI, but I hope to add support for more models soon. Contributions welcome!

暂无评论

暂无评论