"AskHN: what are you working on at the moment?" is quite entertaining. It's like buzzword bingo.
Show HN: Fake Hacker News – See what HN has to say before you post
71–80 of 93 posts
Re: Show HN: Fake Hacker News – See what HN has to say before you post
#72I 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!
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!
Re: Show HN: Fake Hacker News – See what HN has to say before you post
#73Really fun stuff! I'm glad fake-dang is keeping fake-hn a civil place :)
Re: Show HN: Fake Hacker News – See what HN has to say before you post
#74I 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.
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.
Re: Show HN: Fake Hacker News – See what HN has to say before you post
#75This is fun. Had a blast posting my project about websockets in PHP. Nicely done.
Re: Show HN: Fake Hacker News – See what HN has to say before you post
#76Broken on Firefox Windows.
Re: Show HN: Fake Hacker News – See what HN has to say before you post
#77i 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 ho…
Hard to judge without knowing why he's doing it.
Re: Show HN: Fake Hacker News – See what HN has to say before you post
#78Re: Show HN: Fake Hacker News – See what HN has to say before you post
#79Title - 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
Re: Show HN: Fake Hacker News – See what HN has to say before you post
#80I 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.