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: Could LLMs be used to moderate content?

2 点作者 brad0大约 1 年前
Would content moderation be possible via LLMs? If so, would it be cost effective vs human moderation?

3 条评论

defrost大约 1 年前
&quot;I want to stick my long-necked Giraffe up your fluffy white bunny&quot;.<p><i>The Untold History of Toontown’s SpeedChat</i> aka The impossible task of monitoring user content.<p><a href="http:&#x2F;&#x2F;habitatchronicles.com&#x2F;2007&#x2F;03&#x2F;the-untold-history-of-toontowns-speedchat-or-blockchattm-from-disney-finally-arrives&#x2F;" rel="nofollow">http:&#x2F;&#x2F;habitatchronicles.com&#x2F;2007&#x2F;03&#x2F;the-untold-history-of-t...</a>
mooreds大约 1 年前
1. Yes.<p>---<p>Me:<p>Can you please remove any curse words in the following statements? Replace them with asterisks.<p>Fuck the machine.<p>You are a douchebag.<p>What the hell is going on?<p>Shit shit shit.<p>ChatGPT:<p>Certainly! Here are the statements with the curse words replaced by asterisks:<p><pre><code> **** the machine. You are a ********. What the **** is going on? **** **** ****.</code></pre> ---<p>2. Depends. I haven&#x27;t run the numbers on costs. Speed is also a concern.<p>Depending on the kind of moderation, I could see three passes:<p>* regexp&#x2F;algorithmic moderation<p>* LLM<p>* humans (for the thorny stuff the LLM can&#x27;t handle)<p>Full disclosure, my employer has a product called Cleanspeak which does algorithmic profanity filtering. I&#x27;m not close to the product, but I don&#x27;t think there&#x27;s any LLM usage going on right now.
slater大约 1 年前
1. Yes, of course.<p>2. No, of course not. Hire people to make <i>accurate</i> judgment calls, instead of deluding yourself that &quot;statistics on steroids&quot; will ever provide the necessary nuance, just so the CEO can grift his way to a new Porsche.