YHK - yet another hacker news clone

Pointing AI at archives found a forgotten meteorite, lost rhinos, and more

40 points piratebroadcast 8 hours ago 22 comments

whythismatters 1 hour ago | parent

>To make this kind of research accessible, I’m open-sourcing the workflow I created for this investigation as a small toolkit, Antiquity, enabling anyone with a question and a coding agent to conduct similar historical archival investigations.

https://github.com/jessewaites/antiquity

yannis 50 minutes ago | parent

There are also VOC archives at Cape Town, also in Kew (search for the letters of Loot) which were literally looted by privateers. All these are written in High Dutch some in German. How reliable are the translations?

acgourley 54 minutes ago | parent

Very cool.

I'm working on a similar project for contemporary political opinion media. Every podcast, blog, oped, or show cut into little pieces with the structure, speaker, quotes and nouns pulled out and cross-referenced. I bring it up because I wonder if this kind of heavy-weight preprocessing is worth bringing to historical documents as well. It would be much more expensive, initially, but afterwards allows questions get answered even cheaper than they are in your current system. It may be worth collecting interested parties and co-investing in the structured parsing.

Also modern transcription and historical document scanning have a similar shaped problem - dealing with misspelled words and trying to infer their corrections from context.

yannis 45 minutes ago | parent

>Also modern transcription and historical document scanning have a similar shaped problem - dealing with misspelled words and trying to infer their corrections from context. Very true in my case on similar problems, my major issue was OCR relics. Reasonable mispelled words say by an uneducated person, are not that much of an issue. For the OP VOC work most letters were written by educated scribes and less of a problem. Anything before 1650 had very different calligraphy though.

jvanderbot 50 minutes ago | parent

IMHO: The rotating rhino, meteor impact, and animated flowchart is totally unnecessary cruft that makes it look almost satirical. If this keeps up, in time, this "AAA effects" stuff is going to look like the 90s "under construction" banner gifs.

qarl 43 minutes ago | parent

Maybe. But for now, for me, I find them amusing.

yannis 43 minutes ago | parent

What's wrong with the 90s, we had great fun.

jvanderbot 23 minutes ago | parent

It was fun - until it was cringey, then it became fun again due to retro-fandom

Just calling the progression while we're on it.

xenospn 41 minutes ago | parent

I loved it and it brought me joy.

Telemakhos 41 minutes ago | parent

The effects are comically bad. I see the inspiration in scrolling effects that the New York Times put together, but the NYT was never dumb enough to obscure the copy text. Form follows function, and the function of a web page is to be read, not to obscure what is to be read with some stupid effect that's supposed to remind one (I suppose) of a volcano's cloud obscuring one's vision. At least "under construction" banners didn't obtrude upon the copy text.

acgourley 38 minutes ago | parent

I mostly agree, I still read and enjoyed it but part of me kept snagging on the fx and wishing it was way way turned down.

dang 25 minutes ago | parent

Recent and related (by HN's own https://news.ycombinator.com/user?id=benbreen!)

Using Opus 5.5 to discover a new eyewitness record of the dodo - https://news.ycombinator.com/item?id=49926917 - Oct 2026 (79 comments)

sorokod 24 minutes ago | parent

If I sat down to read just the Dutch East India Company pages myself, at two minutes a page, eight hours a day, five days a week, it would take me about 70 years. And that’s before the newspapers. My homebrew AI lab got through the entire archive in a single twelve-hour overnight run.

Makes me wonder how much the author himself learned about the Dutch East India Company. I suspect very little, if anything. Something about these exercises reminds me of junk food: empty calories and all that...

piratebroadcast 19 minutes ago | parent

You know you don't have to comment on everything you see on the internet, right? You're allowed to just keep scrolling when something isn't for you. I wonder how much joy you have in your life, I suspect very little, if anything.

hypfer 17 minutes ago | parent

You're missing the actual point sorokod has.

Specifically that these rabbit holes are useful to bring people to all sorts of new discoveries and skills.

It is important to point out that that's a real risk with such AI use. Of course, it is also true that it would likely not have happened at all otherwise. Both things can be true at the same time.

__

Oh I just realized that you're the actual author and this is not the only super-thin-skinned comment.

Man. Why do be like this.

doug_durham 13 minutes ago | parent

I think the author learned a lot in the process. It exactly served the purpose of diving down rabbit holes.

hypfer 5 minutes ago | parent

Possibly, yeah, but the reactions here do not look like the learnings have been long-term-stable building blocks, tbh.

But anyway.

I am curious what else will show back up again when other people decide to hook up a clanker to one of the many piles of historic (and current) data we do not have the manpower to process for.

sorokod 9 minutes ago | parent

I didn't mean to upset you, piratebroadcast. Like so many of us, you scratched a technological itch, and that is fine. However, now that AI tools have supercharged us, these scratches are easier to achieve, and their outcomes, made public, flood the aether.

piratebroadcast 24 minutes ago | parent

Okay, for those of you that do not enjoy fun, I just added a button at the top of the page to turn off the special effects.

fragmede 13 minutes ago | parent

I liked them! Can't please everyone though.

hypfer 12 minutes ago | parent

I honestly primarily enjoy my browser performance not tanking on this $5000 workstation and actually bailed out while scrolling because it wasn't really usable.

I bet it works great in chrome tho