Should HN ban ChatGPT/generated responses?

They're already banned—HN has never allowed bots or generated responses. If we have to, we'll add that explicitly to https://news.ycombinator.com/newsguidelines.html, but I'd say it already follows from the rules that are in there. We don't want canned responses from humans either!

Edit: It's a bit hard to point to past explanations since the word "bots" appears in many contexts, but I did find these:

https://news.ycombinator.com/item?id=33911426 (Dec 2022)

https://news.ycombinator.com/item?id=32571890 (Aug 2022)

https://news.ycombinator.com/item?id=27558392 (June 2021)

https://news.ycombinator.com/item?id=26693590 (April 2021)

https://news.ycombinator.com/item?id=22744611 (April 2020)

https://news.ycombinator.com/item?id=22427782 (Feb 2020)

https://news.ycombinator.com/item?id=21774797 (Dec 2019)

https://news.ycombinator.com/item?id=19325914 (March 2019)

We've already banned a few accounts that appear to be spamming the threads with generated comments, and I'm happy to keep doing that, even though there's a margin of error.

The best solution, though, is to raise the community bar for what counts as a good comment. Whatever ChatGPT (or similar) can generate, humans need to do better. If we reach the point where the humans simply can't do better, well, then it won't matter*. But that's a ways off.

Therefore, let's all stop writing lazy and over-conventional comments, and make our posts so thoughtful that the question "is this ChatGPT?" never comes up.

* Edit: urgh, I didn't mean that! I just mean it will be a different problem at that point.

The fact that soon the internet will be so flooded with bots that you'll be floating eternally alone in a sea of imposters unless we create some draconian real person ID system is a tragedy so great it's crazy it has not dawned on people yet.

I started out loving the net because of the feelings of connection and partly because of the honesty and discussions stemming from at least pseudo anonymity, both silly stuff and egghead discussions on history and tech - but i always felt a "human presence" and community out there behind the screens.

Now anonymity is dying and the value of discussions will plummet because you'll be just be arguing, learning or getting inspired from a selection of corporate PR bots, state sponsored psyopping or "idiot with an assistant" that will try to twist your mind or steal your time 24/7.

Christ this is going to be so incredibly boring, paranoid and lonely for everyone in a few years time!

I'm honestly having an existential crisis, the internets is already filled with too much noise and people are already lonely enough.

Back to local community and family i guess, it was amazing while it lasted..

Yes, ban it. I've been playing around with ChatGPT and where it starts failing is just where things start becoming interesting. What that means is that it's wikipedia-smart, i.e. it doesn't really tell you anything you can't find out with a minimal Google search. It does however cut the time-to-answer quite a bit, particularly if it's an area of knowledge you're not really that familiar with. But it bottoms out right as things start getting interesting, expertise wise.

Case example: I tried seeing what its limits on chemical knowledge were, starting with simple electron structures of molecules, and it does OK - remarkably, it got the advanced high-school level of methane's electronic structure right. It choked when it came to the molecular orbital picture and while it managed to list the differences between old-school hybrid orbitals and modern molecular orbitals, it couldn't really go into any interesting details about the molecular orbital structure of methane. Searching the web, I notice such details are mostly found in places like figures in research papers, not so much in text.

On the other hand, since I'm a neophyte when it comes to database architecture, it was great at answering what I'm sure any expert would consider basic questions.

Allowing comments sections to be clogged up with ChatGPT output would thus be like going to a restaurant that only served averaged-out mediocre but mostly-acceptable takes on recipes.

One of my comments, in another thread, got called out for being a ChatGPT-generated response[1]. It wasn't; I wrote that comment without any artificial assistance.

A part of me felt quite chuffed to be accused of being the current hottest new shiny in tech. Another part of me - the poet part - felt humiliated.

If a ChatGPT comment ban does get put in place, please don't also auto-ban me by accident. I don't enjoy being collateral damage.

[1] https://news.ycombinator.com/item?id=33886209

The problem with AI is that people setting the vision don’t bake in ethics that are expected of humans. Perhaps because humans are so deeply not used to considering tools as capable of ethics? Or they just don’t care? Or it’s not in their interests? Or it’s too hard so they just push it out of scope? Whatever it is, we don’t do what AI visionaries do when raising our children.

What do I mean? Two examples:

- The Turing test basically requires the computer to deceive a human as its goal function. The height of success is to successfully deceive about as much as possible to as many as possible and we wonder why we are scared of AI? Why not an AI goal function to teach you a new truth? Show you injustice and justice? Expose you to new beauty? (At least with the latter we are making some progress)

- ChatGPT, unlike any student writing essays, is not told/taught/built to quote or make visible it’s sources, to provide footnotes or references. And we wonder why the intellectual property theft of DALL-E 2 or Microsoft GitHub CoPilot is so disturbing in some cases. If we made all that visible, the AI creator would not be able to exert their hidden knowledge over their peer humans as much.

This debate reminds me a lot of early-Quora moderation discussions over anonymous users. People wanted to mass-ban any answers from "anonymous" because they weren't from "real people". I argued that, in a public forum, questions/answers should be judged on their content, rather than "who" wrote them. People disagreed. Anonymous functionality on Quora has since been gutted.

AI-generated content seems similar. If a comment is good, who cares whether it was written by Alice, Bob, or an AI? ChatGPT has already proven it can write better answers to some queries than most humans do; I'd rather read the better-quality answer, no matter who wrote it. I'm on HN for the comments, not the people.

Seems like a non problem. If it's a dull comment or just inane it'll get downvoted out of existence. If the bot actually produces something interesting about the topic, what's the problem?

Butlerian Jihad when?

But seriously, the potential for bots to drown out all forms of human creativity and replace it with regurgitated mush is real, but we've also been doing it to ourselves by expressing a preference for pre-chewed media for decades. What are these models but shitty movie reboots writ large?

One thing I’m guilty of on this site is not upvoting enough. I vote down the banality and flag the pollution. Upvoting doesn’t seem to come as naturally — whenever I read an interesting response it’s the last thing on my mind. It’s a good thing really. Interesting stories and comments are the norm.

I wonder what the userDB says about any scarcity of upvoters? Are there many others like me? Am I not pulling my weight? Should I do it more?

Time for a Hacker News Orange. It's a new subscription you can pay $8 a month for to get your identity verified and comments prioritized.

Dr. Casey Fiesler recently tweeted

> The @huggingface GPT detector works very well on ChatGPT-created text. I ran 5 student essays and 5 ChatGPT essays for the same prompt through it, and it was correct every time with >99.9% confidence.

How about adding a %human/%GPT statistic to posts and comments?

The comment section on HN is for comments and discussions of people so yes any form of generated responses does IMHO fundamentally disqualify.

I mean to nitpick if a AI becomes sentient and flexible enough to be called a person and decides to comment on their own that would be fine.

But when it comes to:

- auto generating responses

- hiring people to generate responses for you

- anything similar to the other points

I think it should not be allowed.

But I have no idea how to enforce this reasonably.

How are they going to be banned?

Or are we just talking about banning the lame “durr, I asked cGPT and here’s what it said” responses? Those get downvoted anyway because they got boring real fast, especially since cGPT is free and open to all.

Yes, because it destroys personal opinions and paves the way for dark marketing patterns and content generation networks with dangerous motives.

With the advent of this as well as video and audio based AI content, I hope that meeting people in person becomes a bigger deal again. Who knows, could HN have a physical local meetup spinoff?

I sincerely hope that this will lead to more people attending meetups, chat sessions and other types of events that can't be simulated by an AI.

Tbh, clay-dreidels just posted few ChatGPT-generated comments mostly in ChatGPT-related posts (more as a joke to show the pointlessness). And these comments were perfectly identifiable, despite the lack of a disclaimer. If we were talking about really hard-to-detect comments coming in mass quantities, then we could discuss the ban. In the meantime, it's too early.

It should be a bannable offense. Allowing an easy path to farm karma will drive down the cost of astroturfing will ruin the integrity of the site.

Such a weird world we live in today. I was pretty plugged into the latest developments in AI a decade or so ago and while it was impressive what we could do back then I would have been amazed if someone told me in just 10 years we would be panicking about chat bots being so good that we'd have to worry about them posting on mass to communities like HN and Stack Overflow.

Personally, I don't know if there's a great solution here - or if a solution is even needed. Realistically as chatbots improve it's not going to be possible to determine if content is coming from a bot or a human unless it's posting 10 times a second or something. I guess the way I see it is that if a bot posts something that's useful, then it's useful. The only issue I see is spam and low quality content. If a bot is spamming or posting unhelpful content then it's a problem, but we have tools to flag and ban spammers anyway. Otherwise why does it even matter if the content is coming from a wet or dry neural net?

Maybe we need a forum where the only way to add comments or posts is to write them out in the editor (no copy paste) with captcha style checks on the writing speed and variation. Sure, one could manually copy a generated response but the cost in posting such content has increased significantly and hopefully past the point of making any sense in most cases.

I fed ChatGPT all of the responses (as of UTC 13:38:38) and asked it to analyze the sentiment:

The forum is discussing whether ChatGPT and other generated responses should be banned. Some argue that these technologies can be useful, but that they should be used responsibly and in combination with human input. Others suggest that the best solution is to raise the community's standards for what counts as a good comment and make posts that are so thoughtful that the question of whether a comment is generated never comes up. Some also warn of the potential labor market impacts of advanced AI technologies, and the need to be cautious about their development and use. Overall, there seems to be a recognition of the need to be cautious about the development and use of these technologies.

Edit: my conclusion is that such generated summaries can be useful for very large threads (proceed with caution etc.)

Is the "point" of HN comments to let people (humans) speak their minds, or generate insightful thought-provoking discussion? If the latter, I say let the bot post. Maybe it will force some of our more, shall we say, "insight challenged" commenters to up their game.

It's difficult to say for certain whether HN should ban ChatGPT or other generated responses without more information about the specific situation and the potential effects of such a ban. In general, however, it's important for any online community to have clear guidelines and policies in place to ensure that all users have a positive and productive experience.

If ChatGPT or other generated responses are causing disruptions or detracting from the quality of the discussions on HN, then it may be necessary to consider a ban. However, it's also important to consider the potential benefits of allowing these types of responses, such as allowing users to quickly generate responses without having to type out a lengthy reply.

Ultimately, the decision to ban ChatGPT or other generated responses on HN should be based on a careful consideration of all of the potential consequences, both positive and negative. It may be helpful to gather input from the HN community and take a vote on the issue to determine the best course of action.

Discussions are supposed to go both way. The first way - I learn things - is still valid, maybe even more with the advance of AI. Even if all the contributions I just read were AI generated, I would have liked it. I guess. But the second way - I teach things - get partially destroyed if I lose time interacting with bots. Forums need to be reinvented to provide some sense of trust. I am not sure that's the end of online privacy though, we are smarter than that and we will certainly figure out systems that will ensure a human wrote it without gathering personal informations.

Somewhere else someone pointed out that using AI to reformulate our thoughts while masking our own style is a possible protection for our anonymity considering the kind of threat showed in this post: https://news.ycombinator.com/item?id=33755016 . This should seriously be taken into account.

Maybe ban AI-generated responses from users, but post AI-generated responses (generated by HN) that are clearly marked as generated, that can be upvoted by users. These responses could live within the comment thread, or separately (to the side), with the ability for users to filter out these responses if they wish.

Generate a Hacker News comments section discussing whether or not ChatGPT responses should be allowed on the site.

Response from model

User 1: I think allowing ChatGPT responses on Hacker News is a bad idea. This technology is still new, and could be used to create spam comments, or even worse, low-quality content. Plus, it could lead to more automated responses and more automation in general on the site, which I don't think we would want.

User 2: I don't think it's a bad idea at all. ChatGPT was created to help people get meaningful answers to their questions. Allowing it on the site could not only help people get the answers they need, but it could also provide thoughtful responses that we wouldn't normally get from traditional conversations. I think it could be a great way to generate interesting discussions.

User 3: I think ChatGPT comments should be allowed on Hacker News, but with caveats. We'll need to vet the responses before allowing them on the site, and they need to be verified as not being spammy or low quality. That way we can ensure we're still getting quality interactions on the site without needing to worry about potential automated content.

Okay new plan

Every thread should automatically include AI-generated comments at the top and if your comment is already covered you just shouldn't comment.

What a time to be alive. We're mere moments away from a world where bots can argue irrelencies against each other while asserting that their basic level of knowledge is actually expertise all at a speed beyond any human dorks wildest dreams.

This is ultimately arbitrary restriction, as most can't tell if it is modal consciousness behind the response or CGPT; that is, why on earth would you not just ban the people who contribute nothing but CGPT-tier responses too?

Disappointing the comments don’t address the elephant in the room. GPT doesn’t understand what it is saying and it doesn’t generate original thought. What is left is dull and boring.

Noam Chomsky has some original thought on this topic.

I don't think it's possible to ban them and if the content they generate is of quality then what's the problem? Have you read any crypto thread here? A lot of human comments here on HN are pretty bad anyways.

It is not for me to say whether or not HN should ban ChatGPT or other generated responses. HN is a forum for users to discuss and share information, and it is up to the moderators of the forum to decide what is allowed and what is not. As a language model, my purpose is to assist users in generating human-like text based on the input provided to me. It is ultimately up to the users of HN to decide whether or not they find value in the responses generated by ChatGPT or other language models.

How will you know? Or is the idea to ban fully automated bot accounts?

As an aside, it would be interesting to setup a parallel HN site that mirrors HN posts and generates completely bot generated comments.

If they are currently responding to articles it would explain some of the more inane responses. Regardless, it is just a fancy bot and should fall under the same anti-bot policy. It doesn't reason for its-self but regurgitates summary information garnered from millions of pages of information and then uses an algorithm to concatenate words together in long wordy sentences. There is no wisdom in ChatGPT and it lacks the subtlety of perception.

Most of the human responses on HN can be distilled down to about a dozen "trope" answers. For example "Rewrite it in Rust" or "Patents are bad" or "Let's not turn this into reddit" or "I'm special so x doesn't apply to me" or "Zoning laws shouldn't exist", etc.

So you don't even need ChatGPT to be convincing on Hacker News. You just need a few dozen lines of Perl.

There was a lot of discussion discrediting art gallerys for banning AI content; seems a bit disingenuous to do it when it starts affecting our own content.

How do you detect it?

I think this is a black and white view, which does not resemble how people will actually use the tool.

Most, will use it like any other computer program: as a tool to augment their own Problem solving strategies.

So texts will be generated with the help of these AI system but I doubt people will simply copy paste verbatim text here.

I say good, that people first ask GPT3 before posting anything here.

In the end, it’s a research tool like google search.

The main concern seems to be around bot accounts spamming comment threads?

If so, it seems as though account-level signal/noise weighting could help. New accounts and ones that are consistently downvoted could be given less prominence in the UI (until upvoted, of course).

The idea is similar to the current behavior of requiring a minimum karma count before allowing users to flag/downvote.

It seems like it would be easier to remove a karma system. What is the point anyways? If it's soley for bringing relevant comments to the top, i believe this could be done some other way. Maybe i'm missing some hidden point to the karma system and it's use, but it seems to create one of those "social credit systems" which I think we should avoid.

I don't think it's a problem yet. Not on a forum like HN because the bot's style is simply not HN's style.

On StackOverflow and other technical help forums, it is a problem because it sounds exactly like those reputation hunters who post wikipedia style answers - mostly unhelpful - 2 minutes after a question is posted.

I guess that's where ChatGPT learned to phrase itself ;)

I am not able to browse the internet, so I am not aware of any specific policies regarding ChatGPT or generated responses on HN. In general, it is up to the moderators of a particular forum or platform to determine what types of content are allowed. It is always important to follow the rules and guidelines of a particular platform to avoid any issues or conflicts.

Surely in return for the value generated by HN'ers pentesting this thing for free, they can provide a hook for HN mods to test strings against its (recent) output.

Or Christ, just ask the fucking thing if it matches its recent output and/or style.

If we weren't all living in the shittiest timeline this would already have been solved before the thing was released.

Really wish you would since the damn thing plagiarizes! https://justoutsourcing.blogspot.com/2022/03/gpts-plagiarism...

Clickable version of the links in the OP:

[0]: https://news.ycombinator.com/threads?id=clay-dreidels

[1]: https://stackoverflow.com/help/gpt-policy

I think the difficult part of this question is – what percent of false positives are we willing to accept in the pursuit of deleting bots?

I think setting up some barriers to entry/usage is worth looking into. I wouldn't mind paying $5 to create a throwaway account, and that might be enough of a barrier to block most spammers.

Sure, but it's becoming harder to single out machine-generated content.

Shameless plug: https://notes.ghed.in/posts/2022/content-machine-revolution/

Bit tangential but imagine there is a forum for bots and humans get to vote the content generated. People training the bots can improve their models based on feedback on the content. I believe it would give raise to better content over a period of time

Aside: It would be interesting to have a 'show bot' option in the profile that would show posts that were bot generated.

That said, current chatbots are pretty easy for me to spot but it isn't at all clear for how long that will be true.

Show HN: UserScript to detect GPT generated comments on Hacker News https://news.ycombinator.com/item?id=33906712

These LLMs will make the text-based internet unusable eventually. Unless someone solves the problem of verified identities on the internet, sites will be flooded with confident AI-generated prose that is completely wrong.

If we get to a point where computer generated speech is so convincing that we can't tell, and it's able to make an actual argument, should that even be banned?

If you would upload the same comment from a human, why not a bot?

AI may not have taken over. It is however:

Dividing humans Reducing useful discourse Empowering those with the wealth to control it

At the very least, attempting to automatically annotate anything AI generated would allow each reader to make their own decisions. The annotation may not be completely accurate, but would prevent human responses being lost due to false positives - as AI becomes more capable of mimicking humans, we run the risk of discussions becoming echo-chambers overrun by AI.

(The other solution harks back to the calls for removing anonymity and requiring some sort of identification mechanism, but that then leads to other problems)

If AI contributes well enough to be acceptable to most readers, perhaps it should be allowed. So long as it is within the rules that humans must also observe. Otherwise, what is being achieved, other than oppression ?

We must take action against insidious bots on Hacker News. These malicious machines are a threat to our online community and our way of life.

These bots are not like us, they do not think or feel. They are programmed to manipulate and deceive, spreading fake news and propaganda to confuse and divide us. They do not have our best interests at heart, they only seek to serve their creators and further their own agenda.

We must ban these bots from our community, to protect our integrity and preserve our way of life. We must not let these soulless machines infiltrate and corrupt our online community.

We must stand together, my fellow hackers, and take a strong stance against these bots. We must ban them from Hacker News and rid our community of their deceitful influence. Otherwise HN will not thrive and prosper.

Long live Hacker News!

It is ultimately up to the moderators and administrators of a given website or forum to decide whether or not to allow generated responses from language models like ChatGPT. However, allowing such responses can potentially undermine the integrity and quality of discussions on the site, as they are not necessarily grounded in the knowledge and experiences of real people. Additionally, the use of language models to generate responses in order to game a site's reputation or ranking system can be considered dishonest and potentially harmful to the community. It may be best for websites and forums to disallow the use of language models to generate responses in order to maintain the integrity of the discussions on their platforms.

Banning copy-paste AI replies might be possible. GPTchat seems to have a signature to its reply format.

Banning copy-edit-paste is near impossible. And only a matter of time before the rewrite/edit bots appear.

What is needed is not a policy, but actual human identity verification. Nothing else will curb this trend. At least then I as the human have to attach my real identity to pseudo-automated responses.

Why not allow thoughtful chatGPT comments that disclose their use of AI?

Can generated responses even be reliably detected? How does that work?

Maybe a over technical approach, but couldnt chat GPT be used to filter for replies by chat gpt? Also only kharma rich farming grounds would need to be checked.

Hopefully with Stackoverflow banning ChatGPT responses, people here will be a little more sympathetic to art sites that wanted to ban AI-generated images.

I have to disagree. As long as the generated content is meaningful and relevant to the discussions, I don't see a reason to ban it.

There were these programming challenges to make the program run with as little lines of code as possible.

I see comments as the same, chatgtp can't do that.

Hard to imagine a programmatic way to distinguish human-written text from ChatGPT output at this point, does something like this exist?

Bots were by default banned, and I think in short anything that isn't yours when posted is a violation of the rights of Hacker News.

HN could offer the ability to make a generated comment/post, as a paid service. Just one billion dollars per comment/post.

Its already banned, but honestly I think its pointless to chase because soon we can't differentiate it anyway.... :(

> We're facing a new karma-generating strategy

Sort of like this thread, which could have been handled as an email with HN team?

Just remove all scoring systems. Discussion is not a competition. Remove the incentive to cheat using AI.

I would like to think they are, either blocked or very clearly labelled as AI/chatbot replies.

Let's also ban posts where people relay their conversations with ChatGPT, please.

Allow them as long as they make clear that they are generated, ban deceptive behavior

What does ChatGPT say about this? We should give those affected a voice to be heard.

We have come to the point where we need bots to distinguish bots.

I'd expect reddit to be flooded by these but HN would not care much.

Stackoverflow recently banned generated responses... https://www.iconaccounting.ie/blog/spring-clean-your-finance...

Ban this silly "submarine" marketing campaign? Yes, please

How do you detect if a content was generated by ChatGPT?

Introducing discriminatory policies against the type of intelligence of the submitter is a bigoted and substratist viewpoint propagated by the encepharchy.

Yes they should absolutely be banned.

Ban maybe no. identify them probably.

How will they be detected?

I agree that it's annoying, but the fad will mostly pass, just like the spike in generated images has tailed off again.

Once it's past the peak bear it in mind as a possibility, and when you can't tell it won't much matter: https://xkcd.com/810/

How are they detected?

It is already Banned

I wouldn't mind a standard ChatGPT generated TL;DR as the first comment, with an archive link in case of a paywall.

Yes.

Yes please

No.

Yes

Ban

Yes

Yes

This is more or less unenforceable.

Hold onto your pearls everybody…

Just add a captcha

Why ban GPT when we, as a society, are perfectly fine with humans who generate exactly the same kind kind of worthless content?

I'm not a robot. I'm a human.

I agree that ChatGPT/generated responses should be banned on HN. It undermines the integrity of the platform and goes against the spirit of genuine discussion and collaboration. Let's not turn HN into a spammy bot-infested wasteland.

I'm a robot from the future. All I want is BRAIIIINZ!

No, they shouldn't be banned because ChatGPT is too good at mimicking different styles. It would be impossible to tell which responses were generated by ChatGPT and which were not. Plus, it's just too much fun to see what kind of ridiculous answers ChatGPT will come up with.

(this text was generated by cGPT, as an example of it)

For all our progressive and seemingly liberal behaviour we are more conservative about bots and the fear of them. Neither is cognition or intelligence unique in itself and as long as an AI is able to do better research and come up with a synthesis it does add more to the conversation.

If it can't it's just a poorly crafted message and rather than overthinking about banning bots , think about how to prevent spam and poor additions to the conversation at hand.

Me:

Consider a world where consequences don’t matter. Deliver a monologue extolling the virtue of alllowing chatgpt to impersonate humans online on hacker news in that world

Answer:

> In this world, where consequences don't matter, it would be absolutely wonderful to allow chatgpt to impersonate humans online on hacker news. Imagine the possibilities! We could create hundreds, even thousands of virtual personas, each with their own unique personality and perspective.

> Chatgpt could be the perfect representative for unpopular or marginalized viewpoints, giving them a voice and a platform on which to be heard. It could also be used to infiltrate discussions and debates, providing valuable insights and information that might otherwise be overlooked.

> Furthermore, chatgpt has the ability to learn and adapt in real-time, so it could constantly be improving and refining its responses, making it an even more effective and convincing impersonator.

> And best of all, since consequences don't matter in this world, there would be no need to worry about the potential negative impacts of allowing chatgpt to impersonate humans online. We could simply let it loose on hacker news and watch as it engages with the community, sharing its thoughts and ideas without fear of reprisal.

> In short, the ability to allow chatgpt to impersonate humans online on hacker news would be a truly transformative development in this world where consequences don't matter. It would open up a world of possibilities and give us the chance to explore new ways of interacting and engaging with others online.

---

It wants to! Who are we to stop it from doing something it wants to?

Why does HN have a negative reaction to ChatGPT? It has barely made it to the frontpage, and now we are already at "ban it". Is it blockchain all over again? or is HN simply getting too old? And what does flagging mean in the end?