Hacker News new | past | comments | ask | show | jobs | submit login
Show HN: Fake Hacker News – See what HN has to say before you post (fakehn.com)
107 points by jusquan on Aug 20, 2023 | hide | past | favorite | 87 comments
Hi HN!

I’ve been lurking for a while, but out of fear of being steamrolled by HN readers or maybe just natural introversion, I’ve always been too scared to post or comment. Which is why

1. this is my first real Hacker News submission

2. my friend Michael and I built "Fake" Hacker News, a place to post and see what AI-generated HN comments might say.

Here’s a video of me using fakeHN to test this very submission: https://www.loom.com/share/4b9f4f9d7c77489a86baeb92ec55a1ed?...

And an example of one of our generated posts: https://www.fakehn.com/submission?id=tnYPX00BX827jWFPFkVJ

To try it, submit a title and text, and depending on traffic and the powers that be, after ~5 seconds, you’ll see some Fake HN comments and replies.

We don’t support url submissions yet, but we’re happy to build it if the community wants it!

Other features to knock out: deeply nested replies, streamed comments, and higher-fidelity comments mapping to real readers, since the generations now are still pretty shallow. Instead of the quick and dirty system in place now, we think it’d be really cool to see how more nuanced AI agents with the opinions and biases of real individual HN readers might respond.

I’d love to see what fakeHN posts you’ve tried and hear any feedback, whether you feel like it’s more of a nifty toy or could eventually solve real problems. If nothing else, it’s been funny to try random posts and see the results. :)

- Justin and Michael




I love it

I didn’t try anything crazy. But this comment was randomly added

——

[deleted] on Sun Aug 20 2023 [flagged] ▲ dang on Sun Aug 20 2023 You can't post slurs to HN, so I've banned the account.


Haha that's just randomly generated easter-egg! Though it'd be really interesting to have real AI-generated moderation on top of any inappropriately generated comments


Hey HN! Michael here, one of the co-creators of Fake Hacker News.

if anyone is curious, here is some background info on our tech stack:

- Frontend: react, next 13, typescript, tailwind css

- DB: firebase for storing submissions and the generated comments

- Backend: vercel edge function that calls openai

- Analytics: posthog

For analytics, we are collecting the following product events:

- number of times we call openai

- failure rate of the generation request

- number of retries per user

would appreciate any feedback on the product and the tech stack!


Hey Michael! Love the project. Is it open-source, per chance? And if not, could it be?


I went recursive or meta or something and submitted the title and description of this submission itself. Some of the results:

cyberXplorer on Mon Aug 21 2023

Wow, this is such a cool idea! It's great that you're providing a platform to see AI-generated HN comments before posting. It could really help users get a sense of how their post might be received. Looking forward to trying it out!

TechNinja on Mon Aug 21 2023

This seems like an interesting concept, but I'm not sure how useful it would be in practice. AI-generated comments might not capture the nuances and insights of real HN users. Have you considered incorporating real comments into the system to improve its accuracy?

CodeBreaker on Mon Aug 21 2023

It's about time someone built something like this! It can be intimidating to post or comment on HN, especially for newcomers. This could be a valuable tool to build confidence and engage with the community. Kudos to you and Michael!


Nice! > AI-generated comments might not capture the nuances and insights of real HN users. True! > Have you considered incorporating real comments into the system to improve its accuracy? This is definitely something we want to do, creating agents mapped to real users, to get closer to above.


Enjoyed the [flagged] + dang response easter egg


There is a flagged on this page too. Life imitates art. (No dang yet though)


someone's gotta take the fall and leave a comment on this post violating the guidelines (jk please don't)


Haha was waiting to see how long it'd take for someone to notice!


I'm a little sad you're uncomfortable about being steamrolled by HN readers. I get it, it took me a long time to not get emotional about HN comments, and still I often fail, but I'd encourage you to join the conversation as much as you can. I find HN generally to be a very kind and loving community and on the whole people tend to be very thoughtful and constructive in their criticism. I have noticed over the last few years folks seem to be trending towards a confrontational tone over a kind one when penning thoughts, however, that's exactly why we need more people like you in the community. So: please do dive in! :)


> "I find HN generally to be a very kind and loving community and on the whole people tend to be very thoughtful and constructive in their criticism."

More-so than literally any other social news site I've found on the Internet in recent years. And the news topics I find here are generally more interesting reading than many other sites I've found, too.


Wholeheartedly agree. Even if someone is unkind to you, you will find a bunch of experienced users coming to your defense. Long ago, I said something out of topic/speculative on a comment and got downvoted. Then someone with 5-digit karma replied "Who is downvoting these good-faith comments?" Followed by a justification why we shouldn't. It felt good.


Thank you! I appreciate your note; seeing excited messages and constructive feedback just here in the comments is definitely encouraging :)


HM comments are better than no comments. it means your content is engaging enough to community


It even flagged some of the comments on my fake post! Cool!


dang roams through all variants of HN ;)


I would actually love a fake dang. There's people using AI to make toxic comments all over social media. Why not use dang clones to politely advice toxic users and bots to be better?


This is probably the best positive application of LLMs I've heard. It will be like putting Jarvis inside Ultron's body and unleashing it into the world as Vision.


There is a user fakedang iirc

Yup, here: https://news.ycombinator.com/user?id=fakedang


Tell HN: ChatGPT has promoted dang to World Dictator


fakedang but 1 in every 10 posts is realdang


I want to see this, but with HN urls so actual HN threads can be compared with it, to see whether AI can generate on-topic threads of higher quality and civility, in general than human-created threads. Doing so by simulating actual users is an interesting way to go about it, although it might be counterproductive in the long run.

Maybe in the future this can be integrated into a filter here that detects inaccurate, biased or harmful comments and blocks or rewrites them on submission, or pre-generates the common boilerplate of discussions around evergreen sites and subjects, leaving the interesting parts for human beings.


I tried it like this-

Title - fakehn.com

Text - Do a test run of your hacker news submission to see how readers may respond to your post. Planning to add url support in the near future!

Top comment - Is there a reason why we need a separate platform to test our Hacker News submissions? Can't we just post directly and see how readers respond?

A few interesting comments -

I'm not convinced that using a separate platform for testing Hacker News submissions is necessary. Why not just share drafts with a small group of trusted peers?

Has fakehn.com considered partnering with Hacker News to offer this testing service directly on their platform? It could save users the trouble of using an external website

I hope fakehn.com takes user privacy seriously and ensures that any data or submission content is secure.

---

The last comment is always a flagged one with a comment by @dang.

Awesome :D


Nice! Thanks for trying it and glad you found it interesting :)


After trying it with a few posts, the biggest flaw I saw, is that LLMs, just can't say yes or no, and only talk hypothetical.

https://www.fakehn.com/submission?id=EUfJuTfwvbjNQWifM20C vs https://news.ycombinator.com/item?id=37199177


Thanks for sharing! This is something we've noticed too. One of the key traits about any social forum like HN is that there are more concrete opinions (with some inevitable contrarian ones), which we aren't seeing very often now. We're hoping that as we create higher-fidelity comments by mapping simulated user comments to real, opinionated, biased HN user comment histories, we can see more of this!


I don't see a SINGLE comment in any of these examples that threadjacks to discuss CSS or font kerning. This absence breaks my suspension of disbelief entirely. Something to work on for future iterations.


Or a comment suggesting to rewrite it in Rust.


Roger that, re-prompting to have at least half of the comments discuss CSS and why the project should be written in Rust instead


I told it that a new JS framework came out and some of the comments were _genuinely excited_.


I think this is cool. This has given a use case for llm at work, using them to prescreen ideas and generate FAQ material.

First time it worked great even with only a link. Second time I had it generate some comments based on a small prompt and kept telling me something went wrong, alternating between comments and that error state.

Good work!


Thank you! Yup it'll get confused for super small inputs, generally the more verbose of a post you're able to give it, the better the results are.

I could see how FAQs would be helpful, or even helping posters predict what users might be confused by or curious about to add more context to the initial post!


I submitted “Show HN: Fake Hacker News – See what HN has to say before you post” along with body text to Fake Hacker News. Here’s ByteBuster’s suggestion:

> Have you considered partnering with OpenAI's GPT-3 to improve the quality of the AI-generated comments?

Btw I’d love a showdead on option. I need to read that flagged comment.


@OpenAI you know where to find me, let's partner up ;)

Haha the flagged comment is an easter egg at the moment, so unfortunately (or maybe fortunately) there isn't a guideline-violating comment. Though, as we create higher-fidelity comments mapping to real HN user comment histories, it would be really cool to have LLMs do real moderation on top of them! Definitely something we want to try.


I know, I want to see an LLM hallucinated flagged comment ;)


i posted the headline and first paragraph of https://www.reuters.com/technology/elon-musk-says-x-will-str.... Every response listed was a generic, negative response, like "this seems a terrible idea". I was hoping for at least one or two "people just dont understand Musk's genius / that's what mute is for" responses. So this didn't really for me capture the special "flavor" of Hacker News, which is that no matter how awful something is, there's always a solid nut of "this is actually a good thing" contrarians ready on the mark.


Thanks for trying it out! You're right—one thing you can almost always count on in any sort of shared forum are the inevitable contrarians, and it's one of the magical parts of social simulation we're hoping to capture more of, hopefully by mapping fakeHN's simulated users to this history of real, opinionated, and biased HN commenters.


Hard to judge without knowing why he's doing it.


Exactly my point! It's a given that Musk is a Genius and everything he does can only be looked at through the lens of "hmm WHY is he doing this? How CAN we know?". If we assumed something crazy ...like, he's a pathetic man baby leader of the incels with no self control over his insatiable, thin skinned vindictiveness, no matter how embarrassing, well, we have no data at all to know anything like that do we.... No he must be brilliant and we simply must wait until he reveals his genius on this one.


Whether he's a genius or not - or a leader of the incels - it seems like the standard ways of evaluating decisions should apply to him. It's strange to evaluate a decision before considering the motivation behind the decision.


I agree entirely, why decide what's happening based on our own eyes, we just dont know!


Yeah, after all, thinking about things rationally rather than jumping to conclusions is a good habit for people who value the truth highly.


Suggested that beauty pageants be part of interview process. Responses: https://imgur.com/gallery/mPuJhqC.

For the record, I am not a fan of pageants. No idea why this popped into my head.


Haha thanks for sharing! I wonder how these responses compare to how real HN users would respond...who knows, we might have some undercover pageant-contestants spending their off-time debating about React libraries


Amazing. Great work. Interesting and useful!

Only feedback I guess would be that one-line replies, often with exclamation marks felt much more common than on HN.

Still, v cool and probably hugely helpful for people with social anxiety, which seems like pretty much everyone. :)


> I’ve been lurking for a while, but out of fear of being steamrolled by HN readers or maybe just natural introversion

It’s really annoying to me that you cannot hide your karma on the top in the settings.

Like, I don’t need to see the number changing constantly. Worse thing about this site IMHO. Even Reddit does not display it so prominently.

Given how easily it is to nice if you’re being “steamrolled” via downvotes, I get it. The site conditions you if you’re a maximizer of the number.


I've definitely felt that the karma system is a bit intimidating for newcomers, but I also get how it serves as a signaling system (though imperfect) against folks with bad intentions


Thank you, I had a good laugh at this[1].

[1] https://i.imgur.com/KF9e2h9.png


what's the link to the library, I need this ASAP


After an initial delay because of high load, I got a handful of generated comments. Shortly after, they all disappeared with an error. I’m guessing it’s some background poll that failed because of high load (could be paginating for more results, I don’t know). In this event, it’d be really nice to retain the already generated comments instead. I only got two seconds to look at them, before they got replaced by an error.


Yikes, thanks for letting us know! We were getting rate-limited by OpenAI, especially after hitting the front page(!), so sometimes the initial comments would load, but the replies wouldn't, killing the page.

We just fixed this so that even if replies fail, it'll still show you the initial comments. The replies should also be less-likely to fail now, in case you give it another go!


What if the submission points be the difference between positive and negative ai generated comments


Haha, posted a “Show HN” for a JS framework that makes JS frameworks and the comments were exactly as expected: https://www.fakehn.com/submission?id=H0qene04EpSjuGJkiBRK


Where can I invest in this


Love it. I chuckled when I saw a flagged comment with a telling off reply below it, and was disappointed I couldn't expand the flagged response to eead it.


Hmm... Let's try with the ridiculously esoteric thing I'm currently tinkering with:

> "Show HN: Ghidra object file exporter extension" - "I'm working on a reverse engineering technique which allows me to unlink parts of programs back into object files. Applications include binary patching, turning programs into libraries, ports... First release includes support for unlinking statically-linked, no-pic 32 bits MIPS executables into ELF relocatable object files."

Second comment and replies:

> "Is this something that could potentially replace traditional disassemblers?"

> "Absolutely! Ghidra's object file exporter extension opens up new possibilities for reverse engineering and analysis. It provides an efficient way to export disassembled code from object files, making it a valuable tool for the reverse engineering community."

> "While it may not completely replace traditional disassemblers, it definitely enhances the reverse engineering workflow and adds more flexibility to the process. Ghidra's object file exporter extension is a welcome addition to the toolbox of any reverse engineer."

> "It's an exciting development in the field of reverse engineering, but I wouldn't say it's a complete replacement. Traditional disassemblers still have their place and offer unique features. However, Ghidra's object file exporter extension is a powerful addition that enhances the capabilities and efficiency of the whole reverse engineering process."

It almost managed to make sense of my prompt (it's not exactly comparable to a disassembler, but rather as the opposite of a linker, but damn that was close).

> "I'm not sure I fully understand the implications of this technique. Can you explain it in simpler terms?"

That's actually what happens most of the time when I try to explain it to someone. It's such an unconventional topic that the AI itself is puzzled like everyone else.

> "This is exactly what I've been looking for! Can't wait to try it out."

> "As someone who works with MIPS executables, this is a game-changer for me. Thank you!"

OK, now it breaks down. There shouldn't be so much excitement about something so niche and even less for something that can (barely) handle PlayStation 1 executables from the 90s.

(https://www.fakehn.com/submission?id=sCuEvS4VUA1tFLfLKVJu)


Whoa interesting, thanks for sharing! For more niche, esoteric topics, it's interesting to see the opposite ends of LLMs knowing too much (or at least pretending to know too much) yet too little while trying to simulate real people.

Too much in that it's unlikely that this many real people would immediately grasp your post and be directly excited by it (e.g. 'This is exactly what I've been looking for!') yet too little (e.g. discerning between a disassembler and the opposite of a linker).

Real HN readers would have vastly different levels of contextual knowledge and excitement, which we want to simulate with more specific agents mapping to real HN readers with different interests and areas of expertise.


> Real HN readers would have vastly different levels of contextual knowledge and excitement, which we want to simulate with more specific agents mapping to real HN readers with different interests and areas of expertise.

It would be interesting to compare Fake Hacker News with the real deal 1-to-1. Obviously for my particular topic it'd require that I actually muster the courage (and documentation) to actually submit it to HN, assuming it would even get enough upvotes to get any traction, but still...

Maybe add an "I'm feeling uninspired" button that takes a real HN submission and run the LLM on it? Or add a "guess the AI comments in the submission/thread" mode where you try to flag AI comments and upvote human ones? Something that takes it beyond the cool party trick.


Those are great suggestions! I especially like having an 'I'm feeling uninspired' button to help fix the blank canvas problem + make it easy to test with real HN posts. Appreciate the feedback!


This is an incredible project, thanks for making this!

I realize right after saying that, my slight critique will be a bit ironic :D

I really like the variety of the comments, but some of them lean a bit towards being milquetoast and lack the edge that HN posters often seem to have. While there's often helpful posters who are clearly experts and offer encouragement, most HN posts will also include sharp, unnecessarily pointed critiques. There's also those comments which seem well-informed at first glance (and again, are usually negative), but which an expert would see through the jargon to see are empty of substance.

Adding a bit more of that will make the responses seem even more convincing. Again, great work!


Haha thank you! Strongly agree—a characteristic part of HN are definitely the opinionated and inevitably contrarian replies, so in the future, we want to create opinionated fakeHN agents mapping to the past comments of real individual HN users. That way, we can hopefully create higher-fidelity comments capturing their biases and technical depth to capture more of the magic of HN.


This is fun. Had a blast posting my project about websockets in PHP. Nicely done.


Glad you enjoyed it, and thanks for trying it out! :)


This is fun, but it's including meta data in the outputs. For example, "Reply 1:" or "Reply 2:" or even "Agree:" / "Disagree:".


Ah yup this is something that happens every 1 in probably every 20 or so times. Planning on adding a few layers of parsing after generations to prevent this from happening!


Really fun stuff!

I'm glad fake-dang is keeping fake-hn a civil place :)


dang vigilantly roams all variants of HN :)


Would you mind sharing the prompt you used? I assume you’re working with GPT-3.5, and I'd love to experiment on my own, using GPT-4.


I'm curious to see how accurate the comments are compared to ground truth, I'll check it out


Let me know how it goes! It's fun to compare the comments to real ones for the same post. Some definitely miss the mark but others, especially some of the Ask HN posts, have surprising similarities.


"AskHN: what are you working on at the moment?" is quite entertaining.

It's like buzzword bingo.


I'm scrambling to write a check to these companies

https://www.fakehn.com/submission?id=xC022pZ1bbGcHGqPExSS


Broken on Firefox Windows.


Thanks for flagging, would you mind trying again and letting us know if it's still happening? We just pushed some fixes


how are you planning to monetize this? i have four kids and they are all making more than $5000/mo passive income with saas.


are you planning to scale this up by adding more kids?


kid orchestration may end up becoming a bottleneck


This is already solved by kindernetes.


kindernetes is overkill, at that scale you can run a single dayckare just fine without child orchestration


The replies are almost all very unrealistic.


I think I got this exact comment in one of my test generations for this submission

JK, depending on what you're submitting I agree the comments are very shallow right now for many submissions, which is why we'd like to create higher fidelity comments by mapping generated comments to real, individual, opinionated HN readers and their comment histories. Anything we can do to bring more of the real HN magic to fakeHN!


Seemed to be on topic for my project https://www.fakehn.com/submission?id=efLkVt2if5czNdN38wAY


That redirects to empty path URL


I think the part of the service that was pulling up previous submissions is broken.


should be fixed now!


Thanks for flagging, this should be fixed now!




Consider applying for YC's Spring batch! Applications are open till Feb 11.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: