Show HN: Extension to filter LLM written articles

#1

Post by nilsherzig » Fri, Sep 11, 2026, 5:14 PM UTC

Firefox Extension/Userscript and API to get Pangram scores for all articles on the hackernews frontpage. The extension allows you to hide articles with a high score.

This is about detecting posts written by LLMs, not posts about AI.

Feel free to use the API to build your own tooling/readers.

Big thanks to https://news.ycombinator.com/user?id=salahadawi for providing the data :).

Show HN: Extension to filter LLM written articles
hnslop.nilsherzig.com

Re: Show HN: Extension to filter LLM written articles

#2

Post by sriyapaka » Sat, Sep 12, 2026, 3:30 AM UTC

How does the scoring work, since AI-assisted useful content is always fine?

Re: Show HN: Extension to filter LLM written articles

#3

Post by nilsherzig » Sat, Sep 12, 2026, 7:02 AM UTC

sriyapaka wrote: post #2

How does the scoring work, since AI-assisted useful content is always fine?

Please explain what you mean by "AI assisted usefull content is always fine".

Here is a detailed explanation from Pangram how their scoring works https://www.pangram.com/research/how-it-works

Re: Show HN: Extension to filter LLM written articles

#4

Post by jordanbuilds_ai » Sat, Sep 12, 2026, 3:33 PM UTC

[flagged]

Re: Show HN: Extension to filter LLM written articles

#5

Post by sriyapaka » Sun, Sep 13, 2026, 3:35 AM UTC

nilsherzig wrote: post #3

sriyapaka wrote: post #2

How does the scoring work, since AI-assisted useful content is always fine?

Please explain what you mean by "AI assisted usefull content is always fine". Here is a detailed explanation from Pangram how their scoring works https://www.pangram.com/research/how-it-works

Thanks for the report.