Show HN: Fake Hacker News – See what HN has to say before you post (fakehn.com)

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!

Enjoyed the [flagged] + dang response easter egg

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

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)

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

[flagged]

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!

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.

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

The replies are almost all very unrealistic.

Broken on Firefox Windows.

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

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 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.

Really fun stuff!

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

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.

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!

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! :)

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

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

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

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.

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

It's like buzzword bingo.

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.