It's interesting but I don't think it belongs as a comment under this post. I can use LLMs to create something tangential for each project posted on HN, and so can everyone else. If we all started doing this then the comment section will quickly become useless and not on point.

▲

Imustaskforhelp 9 hours ago | parent | next [-]

Offtopic but I went to your website and saw that you created hackernews-mute and recently I was commenting about how one must have created such an extension and ranted about it. So kudos for you to have created it earlier on.

Maybe we HN users have minds in sync :)

https://news.ycombinator.com/item?id=46359396#46359695

Have a nice day! Awesome stuff, would keep an eye on your blog, Does your blog/website use mataroa by any chance as there are some similarities even if they are both minimalist but overall nice!

▲

KomoD 9 hours ago | parent | next [-]

I have something like that but as a userscript and with a toggle, it works pretty well for my needs.

Maybe someone finds it useful: https://paste.ubuntu.com/p/rD6Dz7hN2V/

	▲	Imustaskforhelp 6 hours ago \| parent [-]
		Awesome stuff :D Thanks for sharing it.

▲

alabhyajindal 9 hours ago | parent | prev [-]

Thank you! I don't use Mataroa but I can see the similarities. My current blog setup is a Python script that parses content written in markdown and emits HTML. The CSS is inspired by the other minimal blogs I see here.

Thanks a lot for checking out my blog/project. Have a great day!

▲

keeganpoppen 9 hours ago | parent | prev | next [-]

but there is signal in what people are inspired to do upon seeing a new project-- why not simply evaluate the interestingness level of these sorts of mashups on their own terms? it actually feels very "hacker"-y to go out and show people possibilities like this. i have no particular comment on how "interesting" the derivative projects are in this case, but i have a feeling if his original post had been framed more like "i think it's super interesting how easy it is to use via FFI on various runtimes X & Y (oh btw in the spirit of full transparency: i used ai to help me. and you can see more details at <link>). especially because i think everyone who peruses HN with some regularity is likely to know of simon's work in at least some capacity, and i am-- speaking only for myself-- essentially always interested in any sort of project he embarks on, especially his llm-assisted experiments and stuff. but hey-- at the end of the day, all of this value judgment is realized as plainly as possible with +1 / -1 (up- and down-vote) and i guess it just is what it is. if number bad, HN no like. shrug.

	▲	alabhyajindal 8 hours ago \| parent [-]
		I agree that there is signal, and that phrasing his original post as you pointed out would have been better. My issue is that the cost, in terms of time, for these experiments have really gone down with LLMs. Earlier, if someone played around with the posted project, we knew they spent a reasonable amount of time on it, and thus care about the subject. With LLMs, this is not the case.

▲

rpdillon 8 hours ago | parent | prev [-]

Software system is released, comments talk about how to integrate it with other software systems. Seems on-topic.