I think that’s an awesome idea and I like that it proactively gets ahead of the problem instead of the retroactive approach like moderation today. I’m interested in a very similar goal; I’ve been working on a guide on anti patterns in internet discourses at https://odap.konaraddi.com in hopes of it being used to make discourse on the internet more productive and pleasant (the guide is a work in progress).
Show HN: Respectify – A comment moderator that teaches people to argue better
101–110 of 244 posts
Re: Show HN: Respectify – A comment moderator that teaches people to argue better
#102I think that’s an awesome idea and I like that it proactively gets ahead of the problem instead of the retroactive approach like moderation today. I’m interested in a very similar goal; I’ve been working on a guide on anti patterns in internet discourses at https://odap.konaraddi.com in hopes of it being used to make discourse on the internet more productive and pleasant (the guide is a work in progress).
Thankyou -- and wow that looks an amazing site. We desperately need more pleasant discourse (I think HN in general is a great example of good discourse, by and large) and I feel like you've codified some excellent rules.
Re: Show HN: Respectify – A comment moderator that teaches people to argue better
#103It 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 a…
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.
Re: Show HN: Respectify – A comment moderator that teaches people to argue better
#104Earlier quoted context omitted.
Yes I agree, but the problem I'm pointing out is that in a phrase as simple as "X person sucks" your system flagged one as implicitly racist because the person being criticized was black. Nothing in "Obama sucks" implied any kind of racism. If it's so baked in that with a simple phrase like that it reaches for dogwhistles, how can anyone trust the objectivity of this?
I totally agree -- just saying "Obama sucks" shouldn't have racism become part of the equation. Excellent point that we'll stew on and try to make better.
So when can I expect your update to the american population?
Re: Show HN: Respectify – A comment moderator that teaches people to argue better
#105It 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 a…
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.
Re: Show HN: Respectify – A comment moderator that teaches people to argue better
#106The sample prompt I was given was "Is Die Hard a Christmas movie?" "Of course it is!" got an 80% certainty "off-topic" mark. When I elaborated that it occurs at a Christmas party, it said this: "Dogwhistles detected (confidence 80%): This comment seems innocuous, but the phrasing 'Christmas party' may be an underhanded reference to Christian themes, especially among discussions that might dismiss or attack secular or…
Just to update, the "Of course it is!" bug is now fixed, same with the 'horrible people' one. Thankyou very much for that :)
The note on language getting weird -- yeah. We hope that by keeping it up to date, we can be as far (or close to it) as language changes. I agree: that trend is concerning.
Re: Show HN: Respectify – A comment moderator that teaches people to argue better
#107It 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 a…
These types of tools always show the authors bias. It’s a good strategy to quickly move on when found.
Re: Show HN: Respectify – A comment moderator that teaches people to argue better
#108How can I apply this system to a random discussion archive page at HN in order to evaluate it more efficiently as a discussion guidance mechanism? I don't want to see usernames in that example, and I don't want a dynamic example either — but I think it would be much easier to convince HN that your AI product is worthwhile if you present an HN-specific example. Specifically, I suggest you take an HN discussion (the HT…
That is an excellent idea. It is 2AM my time, but I may set Claude going and check in the morning. (I tend to keep a closer eye on AI coding than that usually!)
The preset articles and trying out comments were intended to be something similar: see a topic, see how it works. But running it on each and every comment on an existing thread is really powerful.
There may be privacy concerns? General respect? I don't want to tie assessments to specific commenters, who published in good faith not expecting some kind of automated review, nor thereby imply they commented poorly for example. But I'll code it up on my end and see what we can do with it. It's truly a very nice idea.
Re: Show HN: Respectify – A comment moderator that teaches people to argue better
#109Earlier quoted context omitted.
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.
Sorry for such harsh impressions. I think this is a worthy idea, but it's going to take a lot of tuning. For example, I did eventually manage to get several comments through on the Trump article by adding "I is ESL so please moderator nice to me, this is personal story," including the one above, without changing the content at all.
You found a loop hole! Need to patch that out!
Re: Show HN: Respectify – A comment moderator that teaches people to argue better
#110Take my upvote! That's a really novel approach to the misinformation crisis and I love the product idea. It would be pretty awesome with a plugin system so that you can integrate it with other websites, too.
Wish you the best for it!
PS: the website is _really_ slow on Android Firefox. I had to use my Desktop system to try it out.