Live data from Hacker News

Storm: LLM system that researches a topic and generates full-length wiki article

github.com

1–10 of 104 posts

Re: Storm: LLM system that researches a topic and generates full-length wiki article

#2
Oh dear lord .... sub heading states - Storm - Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models

Good luck with this storm, wiki's the world over. Just a thought but ... maybe someone should ask an org like the Internet Archive to snap-shot Wikipedia asap and label it Pre-Storm and After-Storm

Re: Storm: LLM system that researches a topic and generates full-length wiki article

#3

Oh dear lord .... sub heading states - Storm - Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models Good luck with this storm, wiki's the world over. Just a thought but ... maybe someone should ask an org like the Internet Archive to snap-shot Wikipedia asap and label it Pre-Storm and After-Storm

there is this sentiment of Ai induced deterioration and pollution.

what if that is not the case? what if the quality of this type of content actually increases?

Re: Storm: LLM system that researches a topic and generates full-length wiki article

#5

Oh dear lord .... sub heading states - Storm - Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models Good luck with this storm, wiki's the world over. Just a thought but ... maybe someone should ask an org like the Internet Archive to snap-shot Wikipedia asap and label it Pre-Storm and After-Storm

there is this sentiment of Ai induced deterioration and pollution. what if that is not the case? what if the quality of this type of content actually increases?

It will for a while, I imagine. But the long-term is a concern. Where will new information come from, exactly?

Re: Storm: LLM system that researches a topic and generates full-length wiki article

#6

Earlier quoted context omitted.

there is this sentiment of Ai induced deterioration and pollution. what if that is not the case? what if the quality of this type of content actually increases?

It will for a while, I imagine. But the long-term is a concern. Where will new information come from, exactly?

why not Ai?

And even if we accept the premise (as flawed as it might be) that Ai is not able to create original knowledge, most of what's online is dessimination and dies not represent new information but just old information rewritten to be understandable by a certain segment.

something LLMs excel at.

Re: Storm: LLM system that researches a topic and generates full-length wiki article

#8

I saved a full snapshot of Wikipedia (and Stack Overflow) in the weeks before ChatGPT launched, and every day I'm more glad that I did. They will become the Low Background Steel of text.

The thing is that the Wiki mods will need to be more diligent with uncited things. I also see 2 massive opportunities here. First is that they can have agents check the cited source and verify whether the source backs up what's said to a reasonable degree. Second opportunity is fitting in things only found in other language Wikis that either be incorporated into the english one or help introduce new articles. Believe it or not, LLMs can't generate english answers for things answered only in Russian (or any language) in the training data.

Re: Storm: LLM system that researches a topic and generates full-length wiki article

#9

Earlier quoted context omitted.

It will for a while, I imagine. But the long-term is a concern. Where will new information come from, exactly?

why not Ai? And even if we accept the premise (as flawed as it might be) that Ai is not able to create original knowledge, most of what's online is dessimination and dies not represent new information but just old information rewritten to be understandable by a certain segment. something LLMs excel at.

> Ai is not able to create original knowledge

The current state of LLMs do hallucinate though. It's just not a very trustworthy source of facts.

Re: Storm: LLM system that researches a topic and generates full-length wiki article

#10

I saved a full snapshot of Wikipedia (and Stack Overflow) in the weeks before ChatGPT launched, and every day I'm more glad that I did. They will become the Low Background Steel of text.

Good analogy! There's good reason to believe that web archives "uncontaminated" by LLM output will have some unique value in the future (if not now).
Post reply on HN