LC

Open sourcing a browser extension that tells you when people are wrong on the internet.

By LC.

Published on February 24th, 2026.

There's an image here, with the caption.

I just published OpenERATA on GitHub, a browser extension that investigates the posts you read using your OpenAI API key and underlines any factual claims that are sourcibly incorrect.

Once finished, it caches the results for anybody else reading the same article so that they get them on immediate visit.

If you don't have an open AI key, you can still view the corrections on posts other people have viewed, but it doesn't start new investigations.

I've noticed lately that while people do this sort of thing by pasting everything you read into the chat GPT, A. They don't have the time to do that, B. It duplicates work, and C. It takes around roughly five minutes to get a really good source response for most mid-length posts.

I figure most of LessWrong is reading the same stuff, so if a good portion of the community begins using this or an extension like it, we can avoid these problems.

Here is OpenErrata at work with some recent LessWrong and Substack articles, published within the last week.

I consider myself a cynical person, but I'm a little surprised at what a high percentage of the articles I read make factual claims have at least one or two errors, even with how conservative my prompt is.

When I delete rows from the database and rerun, often it finds different and valid ones it didn't find the first time.

There's an image here.

I published it under my company, but the entire thing is self-hostable and AGPLv3 licensed.

I also made an API available so that providers can use access the results for articles independently and do statistics on them embed them.

Some future additions I and others could work on.

There's a list of bullet points here.

A website for leaderboards forward slash illusorboards, viewing in progress investigations, helpful to the reader reputation mechanics, etc.

Reasoning for known it results.

An appeal or suggestion process that just lets you talk to the AI to point out additional ways articles are wrong, or reasons previous nits are incorrect, that get added to the public list.