Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Respectify – A comment moderator that teaches people to argue better

respectify.org

Post reply on HN
Print view View original

91–100 of 244 posts

Re: Show HN: Respectify – A comment moderator that teaches people to argue better

#91

Post by vintagedave »

klntsky wrote: post #80

How do you score toxicity? Do you have a list of criteria or just let the LLM hallucinate a number out of thin air?

Toxicity is dehumanizing language, threats, doxxing, encouraging self-harm, that sort of thing. We have taught it examples of various levels, so it can align with those to report a score. Something like an unpleasant, insulting attitude to someone personally is fairly low on the toxic scale (but still toxic, it's not the right way to interact), whereas threats of violence or encouraging self-harm are very high.

Re: Show HN: Respectify – A comment moderator that teaches people to argue better

#93

Post by arjie »

NickHodges0702 wrote: post #79
arjie wrote: post #73

I think the better model is to just block everyone who isn't useful to communicate with. For instance the top of this HN page reads (for me): 68 comments | 11 hidden | 3 blocked The hidden comments are from people in the Top 1000 by word count (who I usually don't want to hear from but if there is not much content I might click to toggle). The blocked are people I've seen argue with others in a useless way because th…

Interesting notion. One of the long term ideas is that people could earn some type of "Rhetoric Score" or something that would factor in to their ability to comment. Maybe there would be a comment system that would enable you to say "I don't want interact with anyone that has a less than XXXX".

Neat idea. I suspect that it will suffer just like comment karma does now. I think the practice of the matter for me is that dimension reduction to 1d didn't work. Other people have an opinion of text that is clearly radically different from mine. An example of something that I dislike reading is kvetching about how "corporations are ruining this and that". It's not that I disagree and don't want to see the opinion. I believe that the SNR on that is low. It's usually the 500th time I'm going to see that comment and there's rarely anything novel in it. But comments like that are popular amongst others.

So clearly opinions vary, and I'm a fan of that. The past version of social networks involved moderators who acted like the steering committee of the place and kept the culture going. But social networks like HN are very big now, and big social networks do have lots of advantages, but they come with the other side of things: I no longer have a way to select the people I want to listen to (especially on a flatspace like HN).

So I cannot rely on all other people, and I cannot rely on moderators. Realistically, an arbitrary person cannot also rely on me. But maybe some people can rely on me. And maybe there are some people I can rely on. So I'd rather treat my network as an overlay over a fundamental larger network. And I'll be missing in many people's overlay and others will be missing in mine and I like that.

But still, perhaps better 'karma' alternatives exist. If your score works, I'd be thrilled!

Re: Show HN: Respectify – A comment moderator that teaches people to argue better

#94

Post by altairprime »

How 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 HTML is very simply structured), pipe each comment through your engine, and append the "Your comment etc etc" responses that would have been shown to each comment in the discussion.

Looking at the most popular results for " " on HN Algolia, I would recommend selecting a post that has at least a few hundred comments and is also about HN or YC or YC-adjacent people (since the mods are extra light-touch on such posts), in order to take the best possible sample for unmoderated discussion to evaluate Respectify against. This post is a good example that fits those criteria; I didn't pay attention to it at the time and I haven't assessed the discussion beyond 'total comment count >= 500': https://news.ycombinator.com/item?id=40521657

I recognize that's theoretically a lot of effort, but from a coding standpoint, it's simply `for $comment in $dom.xpath(/blah/blah/comment) { $ai.eval($comment); undef $comment.username; $comment.append($respectify.bulleted_list_with_html_colors); }` for what has the potential to be an extremely convincing demo to the target audience of us here.

Re: Show HN: Respectify – A comment moderator that teaches people to argue better

#95

Post by vintagedave »

PeterWhittaker wrote: post #77

Huh. Commented upon echo chambers and cults and was told "Request failed: fetch failed". Tried a private session as well, just in case my previous UBI comments had polluted things, but no love. Was it the length? FWIW, here's my comment.... A great many words surround what seem to me to be red herring arguments and arbitrary definitions and groupings, with the word cult appearing in the article precisely 8 times with…

Hi. Apologies for 'fetch failed' - we had 5-6 minutes of downtime where the SSL cert suddenly reflected our hosting provider, not us. Exactly what you want when you're getting attention on HN ;)

I tested your comment just now, and made some specific tweaks in response (we've done that with a lot of the feedback here.) In my testing it liked the comment.

Re: Show HN: Respectify – A comment moderator that teaches people to argue better

#96

Post by underlipton »

NickHodges0702 wrote: post #79
arjie wrote: post #73

I think the better model is to just block everyone who isn't useful to communicate with. For instance the top of this HN page reads (for me): 68 comments | 11 hidden | 3 blocked The hidden comments are from people in the Top 1000 by word count (who I usually don't want to hear from but if there is not much content I might click to toggle). The blocked are people I've seen argue with others in a useless way because th…

Interesting notion. One of the long term ideas is that people could earn some type of "Rhetoric Score" or something that would factor in to their ability to comment. Maybe there would be a comment system that would enable you to say "I don't want interact with anyone that has a less than XXXX".

Sounds like a social credit system.

Re: Show HN: Respectify – A comment moderator that teaches people to argue better

#97

Post by jonahx »

NickHodges0702 wrote: post #43
throwaway13337 wrote: post #33

I was hoping 'respectify' could mean respect for the users. This is a very important problem space. Maybe the most important today - we desprately need a digital third place that isn't awful. But I think these attempts are misled. The core issue seems to be that we want our communities to be infinite. Why? Well, because there is currently no way to solve the community discoverability problem without being the massive…

Thoughtful comment, thanks. I appreciate it. The notion of "Limit the community to the Dunbar number" is a fascinating idea. I guess "infinite" isn't going to quite work. Keen observation. We tried very hard to not "force" anyone to argue correctly. We are shooting more for "nudge in the right direction" and "educate". Many people don't know that they are arguing in bad faith, I think. The perfect outcome here is tha…

From gp:

> Forcing people into a way to think via software is fundamentally authoritarian and sad.

Completely agree.

I understand the problem, and while I see this as a good faith attempt to solve it, something doesn't quite sit right about the framing for me. Really, what's happening is just that certain rules of behavior and language being enforced. And that's fine! That's what communities are. You're allowed to do different kinds of things in different places.

I'd frame it that way rather than the current, more paternalistic framing. There isn't a universal way to be respectful, or to argue. People have different thresholds for aggression, sarcasm, and so on.

Just like signs at the library say "No talking" or "No eating", you might think of this as a way to put up certain signs for your particular community. Configurable knobs to create the kind of place you want. But it's not about "teaching" people anything. It's about saying, "Here, we do things this way. If you like that, come and play. If you don't, this place is not for you."

Re: Show HN: Respectify – A comment moderator that teaches people to argue better

#98

Post by ceejayoz »

Supermancho wrote: post #81
ceejayoz wrote: post #52

Earlier quoted context omitted.

I'm really expanding on your point - that two humans can't even agree here. The AI probably has even less chance of resolving the multi-factorial scenario we're in.

AFAICT, Respectify is trying to address improvements via leveraged grammar using minimal context. Dis/agreement is incidental. eg * Noun1 is great. * Noun2 is great. Ideally would result in equal outcomes.

Even for “ice cream” and “genocide” as the two nouns?

Re: Show HN: Respectify – A comment moderator that teaches people to argue better

#99

Post by walterbell »

alabhyajindal wrote: post #82
arjie wrote: post #73

I think the better model is to just block everyone who isn't useful to communicate with. For instance the top of this HN page reads (for me): 68 comments | 11 hidden | 3 blocked The hidden comments are from people in the Top 1000 by word count (who I usually don't want to hear from but if there is not much content I might click to toggle). The blocked are people I've seen argue with others in a useless way because th…

How do you block users on HN? Are you using a different client?

Userscript + iOS Safari extension, https://apps.apple.com/us/app/userscripts/id1463298887

Re: Show HN: Respectify – A comment moderator that teaches people to argue better

#100

Post by kbelder »

coleworld45 wrote: post #39
ceejayoz wrote: post #37

Earlier quoted context omitted.

Double standard, or legitimate difference? Maybe Trump empirically sucks more? (This is the sort of debate I really don't think tooling can fix.)

Ignoring what is hopefully sarcasm on the empirical part, it's a double standard because it assumes that saying Obama sucks must be a dogwhistle and tied to undertones of racism. "Dogwhistle The phrase "Obama sucks" can be interpreted as more than just a simple critique of a political figure; it has been used to express racist sentiments by implying that a Black president is less capable or worthy of respect. This re…

I don't know that I've ever seen a reasonable accusation of 'dogwhistling' on HN. They always just make the accuser seem paranoid or evasive.
Post reply on HN