It seems to have a harder time with political news than more abstract concepts. I was able to pass the checks for the Algorithmic Radicalization and Echo Chamber articles with my first comments.

However, I did not manage to express any opinion on the transgender rights article, from any political perspective, without being flagged. On one of the comments I tested, it gave me a suggested revision from this:

"This is another move in a pattern of limiting the rights of anyone who isn't a MAGA supporter."

To this:

"This seems to continue a trend where certain groups feel their rights are being limited, which could affect many people beyond just MAGA supporters."

The first comment isn't substantive, but the second is even worse, adding so much equivocation that it's meaningless. To add insult to injury, the detector also flagged its own suggested revision. Even if it had gone through, accepting these revisions would mean flooding a platform with LLM-speak, which is not conducive to discussion.

Honest feedback: from a user perspective, the suggestions feel frustrating and patronizing, more so than if my comments were simply deleted. I would stop using a site that implemented this.

From a site operator perspective, the kind of discourse it incentivizes seems jagged, subject to much stricter rules if the LLM associates a topic with political controversy. It feels opinionated and unpredictable, and the revisions it suggests are not of a quality I would want on a discussion board. The focus on positive language in particular seems like a reductive view of quality; what is the point of using an LLM if it's only doing basic sentiment analysis?

Dave here -- I've tweaked a bunch of the internal rules during the HN discussion today, and your comment now passes (using the default settings.)

As for equivocation, that should be strongly dialed down too. It annoyed me too, it was "mush", and did not help. I hope you'll find the current version a lot more human.

I'm grateful for the feedback! Changing it based on all these comments has been intense over the past couple of hours, but boy is it now significantly improved and I am super grateful to you and other commenters.

These types of tools always show the authors bias. It’s a good strategy to quickly move on when found.

Thanks so much for the feedback. Exactly the kind of perspective that we need.

I agree, it shouldn't be like that.

I guess it isn't a surprise that politics will be the hardest topic to moderate.

We'll keep trying to get better. Your comment helps us know where to focus. Thanks.

That rewrite also completely changed the meaning of the comment

Version 1: Rights of non-MAGA supporters are being eliminated while implying rights of MAGA supporters are being preserved.

Version 2: Rights of MAGA supporters are being eliminated with a side effect affecting non-MAGA supporters.