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。

A faster, better way to prevent an AI chatbot from giving toxic responses

2 点作者 nomagicbullet大约 1 年前

1 comment

bradley13大约 1 年前
Much ado about nothing.<p>Look, if you type a bunch of hateful text into Word, surprise, it will display that text on your screen. Would anyone really want a tool that did otherwise? Should Clippy pop up and scold you?<p>It&#x27;s really not that different with LLMs. If some juvenile folks would get a kick out of seeing some hateful stuff on their screens - so what? Why hobble the tools for everyone else?