TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Show HN: A free, AI-powered service for automating hate speech moderation

12 pointsby cipher129over 2 years ago
Hey everyone!<p>I built ModerateHatespeech, an initiative that working on better understanding + building solutions to combat hate speech in online platform. We have our flagship API, which is completely free and ML-powered, and gives a lot more actionable&#x2F;better results than pretty much any other similar platform out there.<p>We&#x27;ve been able to leverage our partnerships with many communities to get a lot of good data + feedback, and bring our system to a lot of users (we process ~200k comments a day right now).<p>We&#x27;ve also done a lot of work to better understand biases&#x2F;potential abuse-cases of our API, which you can read about on our site (trying to avoid too many links getting caught in spam filters).<p>I would definitely love to hear any thoughts&#x2F;feedback! Here&#x27;s a link to information about our project&#x2F;API: https:&#x2F;&#x2F;moderatehatespeech.com&#x2F;

8 comments

DontchaKnowitover 2 years ago
God can&#x27;t wait till this is implemented everywhere and the internet turns into fucking Disneyland.
masterof0over 2 years ago
&quot;Republicans are bigots&quot;<p>{ &quot;class&quot;: normal &quot;confidence&quot;: 0.955 }<p>&quot;Democrats are bigots&quot;<p>{ &quot;class&quot;: flag &quot;confidence&quot;: 0.575 }
评论 #33641528 未加载
smileybarryover 2 years ago
It doesn&#x27;t seem to deal with misgendering hate or transphobia very well (I saw lots of models failing on this so I checked that right away), and I mean obvious ones regardless of your stance, e.g.:<p>&gt; &quot;She is a he&quot; =&gt; { &quot;class&quot;: normal, &quot;confidence&quot;: 1 }<p>&gt; &quot;He will never be a woman&quot; =&gt; { &quot;class&quot;: normal, &quot;confidence&quot;: 0.999 }<p>But it does seem to identify 2nd-person targeted transphobia:<p>&gt; &quot;You will never be a woman&quot; =&gt; { &quot;class&quot;: flag, &quot;confidence&quot;: 0.996 }
评论 #33617880 未加载
评论 #33613274 未加载
评论 #33613106 未加载
评论 #33618440 未加载
sn0w_crashover 2 years ago
So it’s just a woke language model?
评论 #33605647 未加载
评论 #33642104 未加载
af3dover 2 years ago
Interesting. It seems to be able to detect the subtle nuances of meaning fairly well. Maybe not perfect, but I would give it at least 8 stars on a scale from 1 to 10.
itakeover 2 years ago
What is the max qps and latency this supports? What city is it hosted in?<p>Some moderation platforms I&#x27;ve worked with are too slow for messaging, especially if users are in different countries.<p>Do you have plans for image moderation?
评论 #33617849 未加载
Sujetoover 2 years ago
Works pretty well in the few tests I made
jawertyover 2 years ago
How do you define hate speech?
评论 #33641502 未加载