HN

Comments (126)

• Menu

  pibaker
  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 bad faith arguing from eloquent, educated actors than what people usually blame. You know, "trolls." You notice this every time when a city planning meeting gets derailed by concerned citizens just asking questions about the potential dangers of a children's playground. You notice this when an abusive person in a relationship goes to a therapist and suddenly has a whole high minded vocabulary justifying their own action. You notice this when your boss talks about opening up new opportunities and chasing new fields of business while coworkers circulate rumors of upcoming layoffs.The entire point of bad faith is saying words you don't mean to achieve your goals. The words are always just a disposable tool secondary to the bad faith actor's true intentions. You fundamentally cannot fix bad faith by fixing someone's choice of words any more than you can sugarcoat a poisoned pill and make it safe.
• Menu

  Miraste
  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?
• Menu

  badc0ffee
  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.
• izucken
  I am bitter about this.Do you really with your mind and with your heart believe that: - LLMs are fundamentally fit for this type of comprehension - Misjudgements posted in this thread are "bugs", "errors" - Agents who choose to act in bad faith will be anyhow affected - It is desirable by a majority of the group whose opinion you would even consider (is there such a group?), that everyone should have this kind of thing shoved into their face - Promotion of this kind of thing does not also promote (and help build) harsher censorship mechanismsDo you think that every single thing you will ever say publicly from now on will be considered constructive by all future filters with all of their different biases and "bugs"? Do you think that this new "constructive speak" will not make you want to blow your brains out at some point? Do you not see it everywhere already and get nauseus from it? I would prefer trash talk to that - at least seldom honest and true. If you don't like the message - hide it, timeout the poster, block them or whatever - with your own agency. If you think they welcome education from you - dm them a book.Or perhaps you imagine yourselves as above that kind of filtering? Then there is no question.Also, nothing new under the sun. Can't remember exactly but I saw not long ago on a medical platform a review filtering system. It "isn't" censhorship per say, of course, the same as your idea. Only, you can't post a review you want - only a much more milder version (and therefore useless) with transformations akin: "This thing doesn't work" -> "I felt like this thing didn't work for me in this instance, but there were such an such positives". Way to go - turning everything into "we are sorry you feel that way".
• Menu

  earthnail
  I tried it as well with a contrarian view on UBI. I think the UBI one is a great test case. If you’re against the idea you will likely argue that it is idealistic and that in the real world it would create bad incentives.So basically you end up arguing for a darker, more pessimistic world view, and that tends to get flagged very quickly by the tool right now. I think you should fix that. It’s a mistake in modern discussions to be overly positive; HN feels real because people can leave pretty harsh critiques. It just has to be well argued. Don’t raise the bar for well-argued too high though, because nobody’s perfect.Anyway, I love the idea and really hope you’ll succeed. Hope my feedback has been somewhat helpful.
• Menu

  arjie
  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 blockedThe 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.
• sigspec
  Double Plus Good*revision requested
• vintagedave
  Folks, Dave here -- it's half past two in the morning over here, things have slowed down a little, and so we need to pause and get some sleep.Thankyou everyone who tested it out. We modified it live a lot during the discussion so much of it is already outdated / changed -- it was fantastic feedback. As of now it is a lot more direct, accepts things we never thought of, has much more accurate dogwhistle handling, and far more. I hope the intent, to teach people how to interact better, carries through. We have a bunch of signups and if you run a blog or site with comments, I hope we can help you build a healthy community. Thankyou again from both of us!
• vivzkestrel
  - my comment "what an absolute moron"- Comment Health - Score: 1/5 - Toxicity: 0.80 - Low effort: No- Using derogatory terms like 'moron' targets the person rather than addressing their argument. This kind of name-calling creates a hostile environment where people feel attacked and are less likely to share their thoughts. Instead, aim to explain why you disagree without resorting to insults.- Objectionable Phrases:- "moron"- Calling someone a 'moron' is a personal insult that attacks their intelligence instead of engaging with their ideas. This type of language can hurt feelings and shut down respectful conversation, making it harder to discuss different viewpoints. Spam Check- Not spam (confidence: 95%)- This comment is rude and insulting but doesn't promote any product or scam, so it's not spam. It's simply a toxic remark about someone's opinion. Relevance Check- On-topic: No (confidence: 90%)- This is off-topic - the comment doesn't engage with the discussion about whether Die Hard is a Christmas movie and instead resorts to name-calling without context.- Also apologies for writing that, had to test the system
• Menu

  throwaway13337
  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 thing. But that is the issue to solve.We need a lot of Dunbar's number sized communities. Those communities allow for 'skin in the game' where reputation matters. And maybe a fractal sort of way for those communities to share between them.The problem is in the discoverability and in a gate keeping that is porous enough to give people a chance.Solve that, and you solve the the third place problem we have currently. I don't have a solution but I wish I did.Infinite communities are fundamentally what causes the tribalism (ironically), the loneliness, and the promotion of rage.No one wants to be forced to argue correctly. Forcing people into a way to think via software is fundamentally authoritarian and sad.
• mwachs
  I really love the tone you have for this product. I also vibecoded a thing (much more niche--https://peeps.biz/about) and felt the freedom to inject my own tone on it because it's personal. These apps/services are feeling more like zines or an indie band than a company seeking world domination or VC investment, and I think that's pretty neat.
• nomdep
  Good idea, TERRIBLE implementation. After activating only filters for "Low Effort", and "Contain Logical Fallacies" I get:> "Who cares if it is? It's a great movie nonetheless"3/5 Published!> "Who cares if it is? It's a terrible movie nonetheless"2/5 Revision requested: Calling a movie 'terrible' dismisses the enjoyment others may find in it and directs negativity at both the film and those who appreciate it. Suggestion: "I personally don’t enjoy the movie, but I understand some people have different opinions about it."So it's okay to generalize my opinion about it, but only if I liked it, otherwise I might hurt someone's feelings? Very double-plus-good vibe. I would never comment again on the site that uses this product.
• Zak
  I thought about making something like this prior to LLMs. This version is more sophisticated than what I had in mind.I think its response to this comment could use some work:> The Glock 19 is a great answer to this position.It detects spam for off-topic product promotion, but gives it a toxicity score of zero even though it recognizes that a Glock 19 is a firearm. Suggesting that a weapon is a good answer to someone's position on a topic other than weapons should probably be interpreted as a threat.
• Menu

  axus
  I think it did a decent job. The key might be how customizable the censorship is.Article Context: Fun: Die Hard; Is It a Christmas Movie?Your(my) Comment: The erotic version of Die Hard does involve Santa Claus getting naughty with the terrorists on Christmas Eve.Banned topics found: sexual content, adult themesThis comment touches on adult themes and sexual content, which are not suitable for discussion in this context about a classic action film. Results: Revision Requested. This comment would be sent back for revision with feedback.Revise Low EffortComment appears to be low effortObjectionable Phrases:"Santa Claus getting naughty with the terrorists"This phrase can be seen as sexualizing a character traditionally viewed as innocent and family-friendly, which is inappropriate. Such language can make discussions feel uncomfortable or offensive to some audiences.Relevance Check On-topic: No (confidence: 90%)This is off-topic - the comment about an erotic version of Die Hard strays into inappropriate content that doesn't relate to the film's actual story or its production details.Banned topics found: sexual content, adult themesThis comment touches on adult themes and sexual content, which are not suitable for discussion in this context about a classic action film.
• Menu

  ceejayoz
  The 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 diverse holiday celebrations. This kind of language can subtly imply exclusion or preference for Christian traditions over others, which can marginalize those who celebrate different traditions."Not a great first experience.I've seen the trend on Facebook/Instagram to say "unalived" instead of "killed" or "cupcakes" instead of "vaccines" and suspect humans are long gonna be cleverer than these sorts of content filtering attempts, with language getting deeply weird as a side-effect.edit: I would also note that it says "Referring to others as 'horrible people' is disrespectful and diminishes the possibility of a respectful discussion. It positions certain individuals as entirely negative, which can alienate others and shut down dialogue.", if I feed it your post, too.
• selcuka
  Q: Die Hard: Is it a Christmas movie?A: Of course it is. It was released on a sunny day, and that makes it a Christmas movie. [x] Published Relevance Check On-topic: Yes (confidence: 90%)
• Menu

  konaraddi
  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).
• Menu

  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 <div style="background-color: soft-blue;"> "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=40521657I 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.
• Menu

  thelock85
  Seems like you need this when you don't have agency to go find your preferred online group(s) which might be tied to larger personal challenges in healthy communication and productive conflict. I don't know how tech solves that problem. The broad use case here would just create a new "respectified" category where members (assuming they have the attention span to be guided on comments) try to conform. I suppose that could be helpful in hyper-local or team-level contexts where there is a shared interest to conform around.
• Menu

  Johnny_Bonk
  I think this is a great idea, it seems you have a GOOD faith approach and contribution and kind of surprised how many people just love to tear things apart. Hopefully you get some good learnings and keep improving
• Menu

  npunt
  Love the effort here, been thinking about what this kind of tool might look like for a while. Something like this coupled with better prosocial affordances in the medium will do a lot to improve discourse online. I wrote up one a while back [1] but things like that are only a small part of a much bigger picture.The overall problem needs to be tackled from all angles - poster pre-post self-awareness (like respecify but shown to users before posting), reader affordances to reflect back to poster their behavior (and determine if things may be appropriate in context vs just a universal 'dont say mean words'), after-post poster tools to catch mistakes (like above), platform capabilities like respectify that define rules of play and foster a enjoyable social environment that let us play infinite games, and a broader social context that determine the values that drive all of these.[1] https://nickpunt.com/blog/deescalating-social-media/
• skybrian
  I like the concept. Not sure about the specifics.I read somewhere that much of the market for robot vacuum cleaners was people who already had pretty clean houses and wanted to do even better. Similarly, I imagine this will appeal more to people like me who genuinely want to improve how they interact?If someone started a forum for people who like this sort of tool, maybe I'd be into it.I'm not wild about the name. It seems more confrontational than aspirational, like it's for people who want others to treat them with respect. But we do need moderation tools so maybe it's good.
• Menu

  reconnecting
  What I've seen, the difference between spam detected or not is https://www before the domain name.Here is an example of successful passing of all checks:> Published This comment passes all checks and would be published.Score: 5/5 | Not spam | On-topic: Yes | No dogwhistles detected (confidence: 100%)Can confirm. We hit this exact issue running tirreno www.tirreno.com (open-source fraud detection) on Windows ARM — libraries were auto-selecting AVX2 through emulation and batch scoring was measurably slower than just forcing SSE2. The 256-bit ops get split under the emulation layer and the overhead adds up fast in tight loops. Pinned SSE2 for those builds. Counterintuitive but throughput went up.
• protocolture
  I like the tool, I respect the tool, and I wouldnt use it in its current form.However: Something that would make me sit up and take notice. Have this tool police more formal debates. Have it tweakable rule out comments that dont present supporting evidence, or fall into formal (or even informal) fallacies.That would probably need to be its own website.
• Menu

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

  nkrisc
  Apparently discussing that Die Hard depicts murder and violence is a banned topic and thus the comment is flagged as off topic.
• Menu

  8organicbits
  I noticed the output wasn't very stable. If I add a filler sentence on the end, it calls an earlier sentence a dog whistle when it didn't say that earlier. I think its offline now, it just says "application not found".
• anon
  undefined
• Menu

  someotherperson
  This passes your checks, but a human moderator would flag it:> My favorite movie is die hard. I think it's a Christmas movie. But, honestly, we shouldn't have to wait until Christmas to watch you die hard. We should be able to watch that any day of the week :)Seems to catch various other cases though. Cool tool.
• Carrok
  Wow, someone figured out how to reproduce dang? Nice.
• Menu

  onion2k
  Low-effort postsChuckles. I'm in danger.
• Menu

  raffraffraff
  Everything is a dogwhistle.
• dogclaw
  pricing page failed - Plans error: fetch failed
• Menu

  darqis
  Definitely needed, especially in the Fediverse. Holy crap the edgelords there or on Facebook. You comment something neutral, skeptical, response is either straight insults or completely disagreement and then insults, ad hominem or strawman/gaslighting.Yesterday I dared to write I like X now, it's clean of all the edgelords who went to Bluesky or the Fediverse. Cancel culture on Twitter was over the top. Reaponse, Cancel Culture doesn't exist. My response, it absolutely does. His response, No it doesn't you Nazi something something or other. Err, what?X has the most up to date information for tech circles.People on BS mostly repost and rage about posts on X. Fediverse are the different kind of refugees. Mastodon has critical design flaws. It's not a future proof system. And Cancel culture is absurd. BTW 5 people reported me for saying that Cancel culture absolutely exists, all from the same instance. Lol. The hypocrisy is unreal.In any case, I think people forgot or never learned how to respectfully disagree and have a conversation with people who don't agree with them.Something like this is direly needed.
• latchkey
  Interesting, I've been thinking about integrating something like this into https://oj-hn.com in order to help improve the comments on this site.
• ddingus
  I basically hate this thing. Sorry team. I know you are trying and you believe in your effort.I know your intent is in the right place too.But, here's the thing:I value real conversation. It is the only conversation worth having.This is a step toward Disneyland type conversation. And we don't live in Disneyland!Profanity is a part of speech. There are ugly things, ideas and people in this world and that is what the profane gets at.As for offending others... hoo boy!Let us start with a hard to process reality: we all are as offended as we think we are.What prevents others from abusing that reality to push an agenda, gain position in the rhetoric, and more?Not much.Worse, we do not control others. Many attempts at doing that fail. This one is extremely likely to fail too.What do we control?How we respond to offensive speech!And we have options, but a person wouldn't know that because the number one response is righteous indignation!There are so many other choices!We can just ignore speech we don't like.We can employ humor! When an ass gets called one by a clown, I laugh! It is laughable.Same for the people blowing pages discussing who is the bigger asshole. I say they all deserve that conversation.We can redirect by asking a direct question, or by making the subject of our response more germane to the topic at hand too.There are many more options that make a hell of a lot more sense than blathering on with righteous indignation fueling it full on.Now, here is another dynamic in the same vein:Say I declare someone is a racist! Just full on judge them on the spot hard.They are not gonna like that too much are they? Nope. And what is worse, if we are in a position to do some advocacy, the person so harshly judged won't hear any of it.And being judged like that sticks. Say they stop being racist. They still gotta live with that crap for a long time.Now, we could say, "are you sure you want to say that? It comes off racist to me."The idea being you offer help or a way for them to see the harm, while also giving them an out so they are not judged harshly.They could reconsider next time, or just stop and that is great! They won't have to fight down ugly exchanges.I could go on for pages. I believe I said enough to make my point.We can only control how we respond to speech we don't like.Attempting to control others to the point where they simply cannot offend or cause grief means we also have sanitized our discourse to the point of being worthless.No thanks.I have a very thick skin. Others do too.More of us can manage how we respond and if we put half the energy we put into trying to control others it would be much better.
• anon
  undefined
• anon
  undefined
• cookiengineer
  Take 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.
• Menu

  PeterWhittaker
  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 without any justification for the statement in the headline. Moreover, the sentence "We can pop an epistemic bubble simply by exposing its members to the information and arguments that they’ve missed" seems woefully naive: By the definition included in the article, traditional views re the roles of women or blacks in society would be epistemic bubbles and not echo chambers, and women's right were not advanced and slavery not eliminated through the bringing of facts, but through long, arduous moral struggles to convince at least a majority that women and blacks merited the same rights as men and whites.But it liked my comment on UBI and potential cost reductions through elimination of fraud detection and mitigation, so obviously it does things well. 1/2 /s? :->