Live data from Hacker News

Ask HN: Is it time to fork HN into AI/LLM and "Everything else/other?"

news.ycombinator.com

161–170 of 401 posts

Re: Ask HN: Is it time to fork HN into AI/LLM and "Everything else/other?"

#161
One liner you can use in a GreaseMonkey/TamperMonkey script:

[...document.querySelectorAll('.titleline > a')].filter(link => link.innerText.split(' ').find(word => ['llm', 'ai'].includes(word.toLowerCase()))).forEach(el => {const sub = el.closest('.submission'); sub.nextElementSibling.remove(); sub.remove() })

I wrote this in 2 minutes so I'm sure someone is going to reply with something better.

Re: Ask HN: Is it time to fork HN into AI/LLM and "Everything else/other?"

#162
post #139
post #114

People who are a little late to the site may not know there was a time on HN where Erlang has even more frontage submission than the best of AI / LLM. Ruby Rails, Postgres, SQLite, Rust, etc. They all have their moments and I dont think LLM right now is as overwhelming as any other hyped moments. Certainly not Erlang.

I miss the days of daily Haskell posts.

I can imagine you would, with that username :)

Re: Ask HN: Is it time to fork HN into AI/LLM and "Everything else/other?"

#163
post #144

~simonw's demo of a quickie customized HN front-end is great. But ultimately, your browser should have a local, open-source, user-loyal LLM that's able to accept human-language descriptions of how you'd like your view of some or all sites to change, and just like old Greasemonkey scripts or special-purpose extensions, it'd just do it, in the DOM. Then instead of needing to raise this issue via an "Ask HN", you'd just…

Now that is a browser I'd pay for. A genuine user agent, rather than just a browser.

It would also need to be able to "Recognize tasteless, ad-ridden, or other difficult-to-read pages, silently dismiss cookie popups and signup solicitations, undo any attempts to reinvent scrolling, remove all ads except for those on topics X, Y, and Z, and present the page using something like Firefox's reader mode."

Other requirements would include "Fill in these fields that are marked as autocomplete=off," "Use this financial site to display exactly the charts and tables that I want, in this order," "Clean up broken, irrelevant and repetitive search listings on Amazon and eBay," and so on.

For extra credit: "Maintain this persona on Facebook, this one on Bluesky, this one on Slashdot, and this one on HN. Synthesize documents needed to establish proof of age and other aspects of personal identity."

Re: Ask HN: Is it time to fork HN into AI/LLM and "Everything else/other?"

#165
'Domination' in what sense? I could see a couple ways you might mean this, and as qe are HNers of similar "tenure" but as far as I recall more or less otherwise strangers to one another, I could see some interest perhaps in comparing our views of what's changed and how. (Hence being vague here to try to avoid putting too strong a stamp on initial conditions...)

Re: Ask HN: Is it time to fork HN into AI/LLM and "Everything else/other?"

#166
post #126

Earlier quoted context omitted.

That is a wonderful question, but it's very hard to answer without essentially knowing me, and that may be a little bit ambitious for a comment. I'm a software engineer. I consider this some of the most important work of our generation. The hardware we've made today has unlocked an until now impossible control over the world. We don't have to mechanically devise a way to make a clock that tracks the stars. We can jus…

Thank you, I feel similarly. We've become gods of computing through global-scale invention, production, supply-chains, and finance, and we're apparently going to use that power to "improve productivity" which in the best case means cheaper apps that make people more money. I've not heard a single actual use-case for the modern AI/LLM that helps us with our actual national and global problems.

I mean there are plenty of people using AI/LLMs to help with the actual problems, but it's about the same level of proportionality of people generally speaking working on those problems (vs. against or mostly just indifferent). So thus most of AI/LLM use is not in those areas, sadly.

Re: Ask HN: Is it time to fork HN into AI/LLM and "Everything else/other?"

#167

Earlier quoted context omitted.

There is literally an input box to put terms you want to exclude... The prompt asks for "filters out specific search terms", not "intelligently filter out any AI-related keywords." So yes, a good example of the power of vibe coding: the LLM built a tool according to the prompt.

So I have to stay up to date on AI stories just to know what buzzwords I should filter so I don't see AI stories?

Isn't it enough to bury yourself under the rock? - you want the fact of your having done so concealed from you also? But what about the fact of wanting that?

Re: Ask HN: Is it time to fork HN into AI/LLM and "Everything else/other?"

#168

Earlier quoted context omitted.

Wouldn't be hard to train an LLM to do it!

Indeed! Previous: https://news.ycombinator.com/item?id=44261825 I suppose an extension is the answer, classifying and customizing the user’s view accordingly with a pluggable LLM config.

weve just explored a HN site-reskin as a quick way to validate this, and I now use it for my browsing every day. Its a pretty transparent "profile" that gets applied by an llm to rank your HN frontpage, but would be trivial to shift that to a filter.

An extension could be a powerful way to apply it without having to leave HN, but I wonder if that (and our website prototype) is a short term solution. I can imaging having an extension per news/content site, or an "alt site" for each that takes into account your preferences, but it feels clunky.

OTOH having a generic llm in browser that does this for all sites feels quite far off, so maybe the narrow solutions where you really care about it are the way to go?

Re: Ask HN: Is it time to fork HN into AI/LLM and "Everything else/other?"

#169
post #114

People who are a little late to the site may not know there was a time on HN where Erlang has even more frontage submission than the best of AI / LLM. Ruby Rails, Postgres, SQLite, Rust, etc. They all have their moments and I dont think LLM right now is as overwhelming as any other hyped moments. Certainly not Erlang.

It all depends if you care about the tech side of HN or the startup side of HN. I love the tech articles above all else and could easily do without the general trend fluff. With that said, I don’t find the AI posts nearly as bad as the Blockchain era.

As annoyed as I am with the constant deluge of uninteresting AI/LLM articles, I would much rather see a split between tech and startup news. I think that's a lasting and useful distinction.

Re: Ask HN: Is it time to fork HN into AI/LLM and "Everything else/other?"

#170
No. HN is like this. It skews heavy towards startups and right now if you have one of those and you aren't putting AI in your investor propaganda, you're not going to get many investors.

Besides, it's already starting to slow as people realize AI isn't as great as the influencers want you to believe.

Post reply on HN