Pointing AI at archives found a forgotten meteorite, lost rhinos, and more
jessewaites.com
jessewaites.com
People… don’t actually care about what you do, when you succeed. They care about how you do it. You have to be seen to be sweating, struggling, toiling, generally having a terrible time of it - otherwise what you produce is worthless.
Why? Identity. Protection of self from an arbitrary and unfair universe. The internal narrative of “I worked very hard so I deserve this”.
Things which threaten that narrative - be it a child prodigy or a machine prodigy - are very upsetting for people, as they attack a core element of the tale they tell themselves that allows them to survive in this world. That I am valuable, because what I do has value derived from struggle.
At least in academia and tech... the struggle is part of the job, or at least it should be. Basically pre-AI you could be relatively certain that the author(s) went through failure modes and edge cases and weeded them out. This time, not.
I’m so tired of this comment. You’re like the people complaining of vegans and Apple users—I see more of you complaining about the group than there are members in the group. Ironically the thing “getting in the way of appreciation for the accomplishment by some others” is your knee-jerk anti-anti-AI sentiment.
Give it a rest. There aren’t that many comments on the thread still and yours is the top one. No one is contributing more to the anti/pro argumentation than you are. Don’t stoke the flames then complain the house is on fire.
And then I get this useless advice to "give it a rest", as if there were no such negative reaction in the first place, no such parallel drawn between older work and newer work, and as if the counterfactual of what would happen if people were not willing to appreciate such works was not immediate obvious. If there were a substantial contingent on HN claiming that projects done on Apple devices were somehow not real, and trying to shout down Mac-based projects, it would indeed be very tiring, but the problem would not be with people musing on parallels to similar workflows in Linux environments to highlight and acknowledge when a project done on a Mac was good work, nor with Apple fans!
In other words, the contrarian dynamic.
https://hn.algolia.com/?dateRange=all&page=0&prefix=true&que...
> and for a vacuous reason.
I read all top level comments on the thread older than yours, and don’t see any which is “anti-AI”. Yours seem to be the first top level comment which even mentions it.
> Why not reply directly instead? I decided it would be better to positively _appreciate the original work done in itself_
The very first sentence in your comment is criticising others. If your goal was to be positive towards the project, you could have done just that. It wouldn’t stop you from separately replying to (and downvoting) the other unspecified comment with your criticism of their point.
I also liked the aesthetics of it and the little effects (meteorite and volcano, but please fix the rhino and the text flowing around it while it rotates).
I wonder what else could be found in such archives. Some ideas: - Locations or routes of sunken ships and their missing cargo?
- Some pirate stories, maybe about a now-forgotten but once-legendary pirate captain?
- Unusual weather events, like snow in the summer?
(edit: formatting)
The use case is doing original historical research on your phone instead of social media.
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...
> Surely more than if they read nothing at all because most of it would be tedious drudgery of minimal value.
It's an archive. It's all "tedious drudgery" until you figure out the value.
Sometimes figuring out the value means reading things until notice something, which could be a pattern or something dispersed.
Remember that even junk food is more food than junk and you can survive on it for years.
Wether there is enough info to reconstruct usable data is unknown to me but it feels like a good experiment someone could try.
For example with enough information about ship stores/rationing we can learn about how many ships they had, their travel patterns, a whole map of when they were where, the men involved and their whole history.
Alternatively, if there are suspicious gaps then you might find traces of reports that have been deleted, cross-referencing those to ships/officers that didn't report in as usual you might be able to track them to find out more information, etc.
Just calling the progression while we're on it.
exactly why I love it...
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.
I do not know what exactly it is you're building, but the shape also fits "weapon", and weapons do not really care about the good intentions of their author.
Using Opus 5.5 to discover a new eyewitness record of the dodo - https://news.ycombinator.com/item?id=49926917 - Oct 2026 (79 comments)
Many people don’t notice, but even Wikipedia has no normalization between articles in different languages. The language button there acts like its showing you a translated version of the article but its actually a completely different Encyclopedia and community of editors with no cross reference to the other language’s article and references at all. Articles that are stubs on the English page may be massive fully fleshed out articles in another language, and nothing native to the site or anything I’ve seen will tell you that there is more information in one variant
LLM’s can find the word associations and compare them in all languages, even if it itself doesn't innately know language
and there would be so much low hanging fruit here like this engineer found
The Wikipedia folks are working on language-independent, machine-readable structured representation of encyclopedic text (probably relying on something very much like frame semantics, via some sort of general compositional structure) in order to address this issue - see Abstract Wikipedia but note that the project is still at a very early, highly experimental stage. LLMs are not considered adequate for this task because they are non-deterministic and not auditable by humans, hence why a different approach is being planned.
Don’t let perfect get in the way of good
I don’t trust Wikipedia to be incentivized to do this, and looking at the stub about it I have even less confidence
https://en.wikipedia.org/wiki/Abstract_Wikipedia
the last reference is from 2023 before this evolutionary branch of transformers at all
I asked the ChatGPT (I think it was 5.6 medium?) to look at old paintings or sculptures that might contain previously overlooked health issues in the subject.
One of the more famous examples of this is that "Mona Lisa" likely had hypercholesterolemia. The evidence in that case is that da Vinci painted her with a xanthelasma (cholesterol deposit) on her eyelid and a putative lipoma on her right hand.
GPT churned for a few minutes and suggested that the old man in Gustav Klimt's "Portrait of an old man in profile" might have had Frank's sign (a crease on the ear-lobe correlated w/ coronary artery disease: https://onlinecollection.leopoldmuseum.org/en/object/4325-po...).
I told it that the painting was so abstract that I was unconvinced.
It "agreed" and churned a little more and it suggested that the subject in J.A. van Ravesteyn's "Portrait of a Gentleman" (1624) had a clearer sign of Frank's sign that hadn't been previously noted.
I think that one is a little more compelling (https://www.proantic.com/en/1299214-jan-van-ravesteyn-presum...).
For the record, I think this project was an excellent presentation, I loved the interactive elements snd the meteorite (or is that a meteorwrong?) to come across the page. This is about as good of a use of LLM's as I have seen. I didn't see anything about it in the article, but does anyone know what future plans are for this particular project, or is that a wrap? I didn't see I the Where This Stands section anything about future search topics. This really feels like a time where finding the question is every bit as important as finding an answer to that question.
https://github.com/jsoeterbroek/duinroos_replica_goldhat/tre... on Github.
But Here, the start is "What field should I approach and what questions should I ask?"
But this is NOT the same!
When I watch my non-tech friends vibe-coding, I'm struck by how they are so ignorant of basic tech stuff, but little tiny bubbles of "experience" start to percolate in them after a while. Things like "wait, I think this project has weird dependencies that are going to cause trouble when I move it to my office machine" or "hold on, the mobile version doesn't share the same text with the desktop version?"
It is much less interesting to have an attitude of "I don't know or care, just give me a 'result'" vs "Aha! I see where we could apply this in a productive way!"
This is like the Anthropic people feeling like they found many many "very important" Linux bugs https://www.youtube.com/watch?v=NnV_cWeoo5Q - hint: no.
When it's something you know about, the overstating is obvious! It's only when you don't know about things that shallow work (or slop) feels significant.
1. You don't need to be an expert in domain A to comment on that domain, this is credentialism that AI itself is dissolving
2. the fact that your non-technical friends can vibe code this much itself is a proof of (1)
3. the proof that Anthropic didn't find important linux bugs is strange when they did find small vulnvs that could be chained to create real exploits - that's how most attacks were made in the past
4. OpenAI recently dropped 400 proofs solving some of the most important problems in mathematics without any expert in those fields which is a great counter example to you
AI operated by people who know nothing about Turkeye asking broadly "how do I solve the current Turkish political problems" will not get far fast. They might be impressed fast. This is not an argument against AI helping think through things in various ways.
I don't think it's a question of credentialism. It's about being easily impressed.
Finding something in archives is definitely one of those.
I bet it works great in chrome tho