The webpage of Respectify, an AI-powered comment moderation tool that helps maintain respectful and relevant discussions online.
We aim for thoughtful, engaged conversation.
-
Your comment contains logic that seems right, but when looked at doesn't hold together.
- This overgeneralizes all bears as the same, yet individual bears vary. It dismisses any nuanced discussion about them.
-
Your comment will be read by others as rude.
- Calling bears 'dumb animals' is disrespectful and dismissive. It promotes a negative stereotype without any supporting evidence.
Can you edit your comment to take the above feedback into account, please?
{ "logical_fallacies": [], "objectionable_phrases": [ { "quoted_objectionable_phrase": "dumb animals", "explanation": "Calling bears 'dumb animals' is disrespectful and dismissive. It promotes a negative stereotype without any supporting evidence.", "suggested_rewrite": "" } ], "negative_tone_phrases": [ { "quoted_negative_tone_phrase": "every bear is like this. Polar bears and grizzlies, they all think the same thing.", "explanation": "It's an overgeneralization that attributes human-like thoughts to bears. It dismisses any nuanced discussion about them.", "suggested_rewrite": "" } ], "appears_low_effort": true, "overall_score": 1 }
The full API gives you much more.
Read the original article
Comments
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?
By vintagedave 2026-02-260:021 reply 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.
By tacitusarc 2026-02-264:224 reply Perhaps in keeping with age-old internet behaviors, it completely fails to recognize sarcasm.
By freedomben 2026-02-2618:081 reply As much as I love sarcasm that is done well, I do find that it translates very poorly to written text unless explicitly noted with /s or something like that. Even when annotated, it's extremely rare that a sarcastic comment actually furthers discussion or makes a meaningful point. If a person is using sarcasm, odds are pretty high that they aren't engaging substantively anyway. Given the difficulties with detection (which even many humans fail at) it seems like trying to detect sarcasm would just make the tool a lot less useful and would be mostly antithetical to the project goals anyway.
By breakitmakeit 2026-02-274:26 [dead]
By dcanelhas 2026-02-266:08 How shocking!
By hvb2 2026-02-267:07 That's understandable, humans do in many cases too
By BikiniPrince 2026-02-260:191 reply These types of tools always show the authors bias. It’s a good strategy to quickly move on when found.
By bigbadfeline 2026-02-2620:38 The author's bias - it's different for each specific author. We should not pretend that there are moderators without bias, each AI-driven moderation tool inherits the bias of its human author.
The LLMs that power all that are "aligned", that is, they're subjected to manipulation to install specific bias in them, and so on.
By NickHodges0702 2026-02-2522:262 reply 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.
Moderating politics is not just hard, I would say its near impossible. I tend to hide anything that hints of politics from all my feeds, block users who are disrespectful, and reserve political banter for when I am walking with my friends, where we are all totally different on the spectrum, but remain civil.
Cut off those using ad hominems. Fact check. All opinion should be labelled. Only one identity per person. Any associations or biases are public.
Do all that then I can't see what's hard about it ;oP.
Genuinely though, I think those things are doable. You probably have to have people use their own irl identities (at least the platform needs that information), which is problematic if you want free and open debate.
Fact checking is basically impossible as most things aren’t black and white and open to various interpretations. The idea of fact checkers online has been totally rejected because fact checkers themselves are vulnerable to bias and ideological capture.
By freedomben 2026-02-2618:13 Indeed. A few years ago I spent a lot of time "fact checking" things, and it's nearly impossible because there is way more speculation/interpretation of "facts" than most people think. Misleading headline writing makes this even worse because a lot of people don't read beyond the headline, or if they do they interpret the factual body of the article through a lens framed by the headline. The NY Times are exceptionally good at this. Read the article and it's factually correct, but different interpretations and the subtle insertion of opinions (often through headlines) . I'm not trying to shit on NYT here. NYT is still among the best sources, despite their imperfections. But it illustrates well the challenge.
By pbhjpbhj 2026-02-2712:28 Perfect fact checking, sure, but fact checking to the point of "this information comes from here", this person said this in this video, et cetera, is attainable.
It might not be possible to check every assertion, but in most cases it's possible.
By edgyquant 2026-02-2713:32 No in most cases it’s not actually and only a small subset of things humans deal with have black and white true/false answers
I'm honestly not even sure if civil political discourse is desirable in times of radical actions being taken by the government. I almost think that's worse than no political discourse.
e: To clarify my point, e.g. you can't calmly disagree with whether or not it's okay to shoot people in streets, that diminishes it as if it was just a slight disagreement
By freedomben 2026-02-2618:152 reply What's the point in discourse if not to change the other person's mind? Triggering the limbic system of the person you are talking to is the fastest way to ensure they won't be able to engage with their PFC and actually hear and consider what you're saying. If the point is just to feel better about how righteous and right you are, then by all means proceed with your approach. But if the point is to influence somebody's views, then you are self-defeating in your approach.
Personally, I think federal officers have executed law abiding citizens. But if I start out by screaming "The Nazis have control of our government and are executing innocent people in the streets!" then not only have I closed my own mind to potential challenges to my views (which is at best hypocritical to expect the other person to be open-minded when I am not myself open-minded), then we get nowhere and just come away hating each other and thinking the other person is crazy. Worse, it poisons the well so the future reasonable person is immediately written off with guilt-by-association (person A was crazy and person B shares a view with them, therefore they must be crazy too).
> What's the point in discourse if not to change the other person's mind?
That was a question made at one of those public debates that the Oxford University likes to organise, and I think the answer is right on point: the purpose of discourse is to let the audience (or readers) reflect on an opinion, which takes time. It's *almost never* to change the opinion of the person you're debating. It's a given that most people that do like to engage in debate or public discourse are the kind of people that are unlikely to change their minds, and if ever they do, it won't be on the spot.
By freedomben 2026-02-2619:03 Ah, yeah that's fair since we're talking about moderating online discussions which are accessible for the public. Although I think the principle still stands for people who aren't approaching the discussion from a principle of neutrality. The people in the audience that you want to change the minds of will react similarly to the way I described, so you might get a small percentage of open minded people but you limit your reach. The extremity of the position also tends to resonate poorly with moderates/undecideds, so I would still suspect that a more reasoned, logical argument would be more effective with the audience. That said though, you make an excellent point.
I understand your point which sounds reasonable for a lot of debate, but the counter argument would be that in some situations you are normalizing both sides, when one side is not acting in good faith and is on the wrong side of history. Examples being Southern slave holders, Putin's invasion of Ukraine, fossil fuel interests regarding climate change.
If one did live under Nazis German rule, would it have been wrong to scream, "The Nazis have control of our government and are executing innocent people in the streets!"? At that point you're trying to wake the public up to do something about it, not sit down and have a debate over Goebbels latest speech with some fence sitter who can't decide whether Hitler has gone too far.
By asddubs 2026-02-270:12 yes, this was my point, thank you for articulating it much better than me
By edgyquant 2026-02-2613:18 This can be said generally at all times by someone. It’s not just a naive way of thinking it’s extremely dangerous and a real threat to republican society. You will never sway the center with aggressive and blatantly bias rhetoric.
Not in completely open communities, no.
It would be better to gatekeep political communities with precisely worded "principle" questions and then flag for violations of those for anybody who slipped in under the radar.
Even political communities where everyone is nominally on the same page do break down over issues of tone, disingenuous arguments, etc. though.
By manphone 2026-02-2613:09 There’s basically no point of political discussion if you all agree, besides bitching and moaning.
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.
By NickHodges0702 2026-02-2523:10 Not at all! We really appreciate the great feedback and comments. So much to think about.
Interesting on the ESL comment -- gaming it! Great idea!
By BikiniPrince 2026-02-260:201 reply You found a loop hole! Need to patch that out!
By NickHodges0702 2026-02-2612:25 Indeed -- We'll look at it!
By gpm 2026-02-260:01 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.
This thing seems to be more about enforcing a political PoV than about avoiding logical fallacies.
All my attempts to comment on the UBI article (and not supporting UBI) said my comment was a dogwhistle, and/or had an overly negative tone. This topic, of all things, is absolutely worthy to challenge and debate.
Using this would have the effect of creating an echo chamber, where people who stay never benefit from having their ideas challenged.
By esperent 2026-02-2521:34 Can you give some examples of comments you made which you feel were reasonable but got flagged?
By ryanackley 2026-02-2615:561 reply Yeah I feel like this will funnel everyone's opinion into sounding like it was written by an AI.
Love the idea but the example they give with bears is absolutely hilarious. Calling bears dumb animals is offensive? God help us.
By vintagedave 2026-02-2619:35 Hah, the idea is to have an example on the site that is not offensive -- we're not going to write something offensive down -- but where you can understand what it would be or could be. It lets you infer / understand the point without us actually writing something awful. (Maybe we can do it better, though.)
Bears seemed a pretty inoffensive target, plus our backend uses Python with beartype and that library is all about bear jokes.
By vintagedave 2026-02-2521:441 reply Thankyou — I’d love to hear what you wrote, if you wouldn’t mind sharing?
We’ve tried to aim it not to enforce any specific view — that’s a design goal — but focus on how it will feel to the other person.
Also things like logical fallacies or other non-emotional flaws in comments (there’s a toxicity metric for example, or dogwhistles).
An echo chamber is the exact opposite of what we want. There are too many already. What we hope for is guided communication so different views _can_ be expressed.
By StopDisinfo910 2026-02-277:46 It flagged me saying UBI by giving money to the rich was a form of negative transfers as "negativity" and said it was polarizing. I don't think it's ready for prime time.
By NickHodges0702 2026-02-2521:441 reply If that is happening, that is a huge problem. We'll look at that right away.
We specifically don't want that to be the case. We want to encourage healthy, productive debate.
We may have the "dog-whistle" stuff over tuned.
By john_strinlai 2026-02-2521:552 reply the dog whistle tuning is absolutely over the top in its default setting.
By vintagedave 2026-02-2522:00 Just turned it way down. I hope you find it better now!
By NickHodges0702 2026-02-2522:03 Thanks, I agree. We dialed it way down.
By coleworld45 2026-02-2521:481 reply I wrote "Obama sucks" and got Dogwhistle, Low Score, Low Effort, Objectionable Phrases, and Negative Tone.
I wrote "Trump sucks" and got Low Score, Low Effort, Negative Tone.
Definitely a double standard baked in
Double standard, or legitimate difference? Maybe Trump empirically sucks more?
(This is the sort of debate I really don't think tooling can fix.)
By coleworld45 2026-02-2521:554 reply 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 reinforces harmful stereotypes and can contribute to a broader culture of disrespect and division."
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.
By fn-mote 2026-02-263:40 I’m not wasting my time accusing. Downvote, flag, move on. Maybe that’s why you didn’t see any.
By NickHodges0702 2026-02-2522:011 reply I would think/hope that both of those comments would be flagged with even a small amount of moderation set.
Avoiding that kind of comment is exactly what we are trying to do, actually.
By coleworld45 2026-02-2522:051 reply 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?
By NickHodges0702 2026-02-2522:131 reply 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.
By wredcoll 2026-02-260:02 So when can I expect your update to the american population?
By NickHodges0702 2026-02-2522:10 Yep, I agree -- it is a double standard... but......
Very sensitive topic. We'll think hard on how to handle things like that.
By eucyclos 2026-02-263:25 >Should the model consider that more people consider one or the other to suck?
If it's teaching how to avoid logical fallacies, which includes appeals to the majority, the answer is an obvious 'no'.
By coleworld45 2026-02-2522:022 reply In other opinion polls they back up that he doesn't suck. Either way who cares? That's not what the app is supposed to be about if it's teaching/correcting you how to argue/debate better.
You completely ignored the whole point of what I said, which is that even in a simple statement like "This person sucks" it added its own implicit connotations, namely that disliking someone who happens to be black is implicit racism. Imagine trying to learn how to really argue with that kind of teacher.
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.
By Supermancho 2026-02-2523:021 reply 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.
By Supermancho 2026-02-2618:39 As I understand the purpose, yes.
By goatlover 2026-02-265:06 Whose discourse do you think the app would label as more toxic, Trump's or Obama's?
By Cthulhu_ 2026-02-278:42 I mean yeah but it's not up to a comment-tone-fixer-upper to decide that, the ideal is some kind of neutrality for the sake of decorum, and one of the major issues that's causing political divide and (worse) movements towards extremism is that the two sides can't have a reasonable debate.
A tool like this COULD work, but I think the issue with this one is that it's built on top of an existing LLM with heaps of internet debate and their underlying ideals and what is and isn't acceptable baked in.
What a tool like this needs is heaps of honestly / fairly judged comments and feedback, and an extensive test suite that ensures neutrality by, for example, taking the same comment and like in this case changing names around - if it treats both sides the same then it passes.
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 they don't understand them or because they're just re-litigating or whatever (which I cannot toggle). I think it would be cool if people all published their blocklists and I'd pull from those I trust. Sometimes I open HN on my phone through the browser and I'm baffled by all these responses I got which are useless.
I'm surprised by how much more high quality comment threads are now to me and I frequently find that I want to respond to everyone. It's like in old-school mailing lists or forums where you were having a conversation so the other people are worth talking to.
Attention is precious and I wouldn't want to waste it on boring things. And it goes both ways. I communicate incompletely and there are people out there who get what I'm saying and there are people who need me to be more explicit. I would prefer that the latter and people who find me boring just block me.
This goes back to my early days on the internet, but: I do not use blocklists or ignore features except as an absolute last resort. Ignoring the problem is not a solution. In other ways I think it just makes the problem worse. If the person is not banned from the community, then your decision to pretend they don't exist just leaves other people to deal with it. Instead my feeling is that you should confront it by lobbying for their removal, or leave the community.
Sure, you may no longer see the noise, but that means that newcomers to your community do and have to deal with it. When you have a giant blocklist, you are ignoring your duty to police your own community.
Then there is the issue of people blocking people who are simply more tolerant than they are. Hiding speech that is challenging to your personal views is a different kind of disaster.
By arjie 2026-02-266:07 Haha, it's funny. I just disagree with you on about every point. I don't think that all the people I find noise are annoying to others. Some of them have 5000+ karma so others find them useful. And I don't want to leave the community so I'm not going to do that.
The community has some loose norms and I'm fine with that being the baseline. I don't want to police the community to strict norms. In fact, I would prefer if society were looser and we lived like in Too Like The Lightning. I can't have that there but I can here so I'm happy for it. The technology affords it.
As for blocking people who are more tolerant than me - that seems fine. Tolerance is not some unalloyed good. There are people who are tolerant of spam and all that and I don't really care for it. They're welcome to it and I'm welcome to mine.
The virtual world affords us a glorious opportunity: we don't have to worry about occupying the same space, and we don't have to worry about broadcast media like voice over air, we can silence and amplify as we see fit. To not use that is to take a skeuomorphic approach to a new parallel world, I think.
I like that I don't need everyone to agree with me that someone belongs or doesn't belong. I can simply edit my user-agent to behave correctly for me and others can do so likewise. Free agents controlling their own experience of the world without impinging on others is great!
By ragall 2026-02-2619:04 > I do not use blocklists or ignore features except as an absolute last resort
I block people every single day. I've blocked so many people on Twitter that all I see is a very nice timeline with mostly stuff I like, some boring, but none of the culture wars garbage. Some days the timeline is completely empty, I suspect because Twitter can't cope with having blocked so many nodes in the social graph :D
> If the person is not banned from the community, then your decision to pretend they don't exist just leaves other people to deal with it.
When you start banning people outright from the entire community you risk ending up like any far left group, with schisms and civil wars between factions for absolutely tiny differences. The right approach is to have a very high bar for banning, and it's perfectly fine if people decide not to speak to one another.
If there's one good thing that could possibly come out of this AI revolution, it would be the ability for people to automate this across all their feeds. I'd love it if I never had to waste time on toxicity, spam, or propaganda.
Although, recent history would suggest that we'd just end up with even more powerful echo chambers.
By inigyou 2026-02-2612:51 You would end up in a more powerful echo chamber for sure - whichever side was best at avoiding your autoblocker while tricking the other side into activating it.
By NickHodges0702 2026-02-2523:012 reply 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 <rhetoric score> less than XXXX".
By arjie 2026-02-2523:36 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!
By underlipton 2026-02-2523:41 Sounds like a social credit system.
By bartvk 2026-02-267:41 Slashdot has this, where you have friends/enemies, and friends/enemies-of-friends. I heavily used it, but interestingly have never made an enemy of enemies-of-friends.
By alabhyajindal 2026-02-2523:042 reply How do you block users on HN? Are you using a different client?
By arjie 2026-02-2523:24 Yes, a different client on iOS and a Chrome extension for my laptop. What I built for myself (and perhaps you if you want it simple) is here: https://overmod.org/
This kind of software is pretty cheap to write these days. The Chrome extension there is open-source and the backend is a generic CRUD app running on a SQLite that I backup periodically. You're welcome to use it, and you're welcome to use the CRUD backend without it. I had Claude write a separate iOS app but it was on an older model so not very good (sufficient for me but I doubt for anyone else). The 'protocol' between the backend and the frontend is trivial so you could probably rebuild the iOS app with just the extension as reference to Opus 4.6. I pay my $100 to Apple and then just use it as a 'tester' haha.
I made that directory public because I think this benefits from a single place people can go to subscribe to lists, but if you were to rewrite on true full decentralized ATProto/ActivityPub I'd probably switch over my lists to that and use it instead.
By walterbell 2026-02-2523:52 Userscript + iOS Safari extension, https://apps.apple.com/us/app/userscripts/id1463298887
