Live data from Hacker News

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

respectify.org

151–160 of 244 posts

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

#151
Hmm, I'm in 2 minds about this. The best online communities I've been in have been small & come across more human and the thought of "this is a person you're replying to" was innate. On larger forums a nudge towards that humanity might be good but I think this at times goes beyond a nudge and is more of an opinionated telling-off, which a lot of people aren't going to react so well to.

I wonder how this would be as a light touch plugin for the browser that would review a comment in context and possibly help test and refine the content.

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

#152

I think the premise of this tool is flawed. Bad faith actors are not people who write poorly or aggressively because they don't know how to express their beliefs like a polite, college educated white collar professional. They are people who have an agenda to push and are willing to use whatever rhetorical techniques allowed to achieve their goals. I would even go as far as saying that we are under more threat from ba…

Your point definitely stands, but I feel there is still a good faith use case for this.

I've definitely been young and passionate and, occasionally a bit inebriated and/or triggered by certain things when I commented on the internet (in fact I'm usually silent unless I've had a few drinks).

Though I don't think myself a bad faith actor, I've definitely written things I shouldn't in the past. Often with good intentions, but perhaps with anger or passion clouding my judgement. Most folks have something that will trigger them to respond in a sub par way after a bad sleep or a long day.

I'd like to think that a tool to let me know I'm alienating rather than persuading the folks I'm talking to would provide benefit.

But yeah. This is a difficult one. Not everyone who is being a jerk is just having an out-of-character bad day.

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

#155

I think the premise of this tool is flawed. Bad faith actors are not people who write poorly or aggressively because they don't know how to express their beliefs like a polite, college educated white collar professional. They are people who have an agenda to push and are willing to use whatever rhetorical techniques allowed to achieve their goals. I would even go as far as saying that we are under more threat from ba…

I came to realise many people do not know how to lead an insightful discussion. They in fact might not even know how to make the point they are making in a way that other people can understand what they meant. In short: people suck at communicating.

Now a tool that gives people feedback before their comment is going out could be tremendously useful to the quality of the conversations people could have.

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

#156

I think the premise of this tool is flawed. Bad faith actors are not people who write poorly or aggressively because they don't know how to express their beliefs like a polite, college educated white collar professional. They are people who have an agenda to push and are willing to use whatever rhetorical techniques allowed to achieve their goals. I would even go as far as saying that we are under more threat from ba…

> I think the premise of this tool is flawed. Bad faith actors are not people who...

I think there's something here. The tool is not intended to stop bad faith actors. You can't stop those. But you can nudge people into "being better" with a simple prompt. I can't recall the exact blog/paper now, but I remember reading that someone did this test (google perhaps?) and saw that with a simple prompt "hey this message is high on anger, did you mean to write it like this?" before submitting lead to ~30-50% to change their message and tone it down. It might help in that regard.

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

#157

I think the premise of this tool is flawed. Bad faith actors are not people who write poorly or aggressively because they don't know how to express their beliefs like a polite, college educated white collar professional. They are people who have an agenda to push and are willing to use whatever rhetorical techniques allowed to achieve their goals. I would even go as far as saying that we are under more threat from ba…

Very eloquently put :) I agree with your proposition that bad-faith actors often mask their true intentions behind polite or sophisticated formatting.

However, I think a tool like this could still have huge potential, but less for tone and more for structure.

E.g.: - Atomicity: Ensuring a comment presents a clear, self-contained core argument that can be debated in sub-comments, rather than a tautology or an accumulation of loosely connected arguments.

- Logical consistency: (Though whether an LLM can reliably parse logic is another question entirely!)

- Citations: Checking if the commenter provided credible sources for their claims.

- Civility of Discussion: instead of it becoming another mud battle

- Misinformation: Flagging the use of known, debunked conspiracy theories: Instead of modifying the original comment, it could simply append a contextual banner to the top with a Snopes link when a known false claim is made.

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

#159
> Current moderation tools just seem to focus on deletion and banning. Wouldn’t it be helpful to encourage productive discussion and teach people how to discuss and argue (in the debate sense) better?

Yes, but an awful lot of people aren’t interested in that.

I think a tool like this would be helpful for banning. LLMs are probably not reliable enough to make banning judgements themselves, but an LLM that pops up “Are you sure you want to post that? It seems to break these rules…” makes it very easy for human moderators to ban quickly and permanently. It provides incontrovertible evidence that the poster intended to break the rules but it still offers an escape hatch for when the LLM gets it wrong.

Post reply on HN