AI Model Opus 5.5 Uncovers a Lost 1615 Account of Dodo Hunting
Using Opus 5.5 to discover a new eyewitness record of the dodo

Historian Benjamin Breen describes using the AI model Opus 5.5 to search the Dutch East India Company archives, where it found a previously unnoticed 1615 ship's log that mentions catching dodos. The model also surfaced a possible new reference to the extinct red rail and a theory linking a Portuguese Jesuit's 1616 'ostrich' to the dodo painted for Mughal Emperor Jahangir. Breen argues AI excels at tireless archival searching but still needs human experts to ask the right questions and judge significance.
The main thing that contemporary AI can do for historical research is, in effect, the digital equivalent of counting sheep. Because they never get bored, they can search through enormous datasets to find new evidence for existing claims (or, potentially, disprove them).
- nl
> Epistemological weirdness
> They are also notably bad at judging the historical significance of what they find.
I use LLMs for some things that are outside the more common use-cases (in my case 3D design for 3D printing) and one thing I've noticed is that the errors it makes are so completely unlike human errors that they are hard to anticipate.
It will do things like build perfect snap catches but put them so the the pieces they are connecting are rotated 90 degrees from how they should be. It's "dumb" error, but hard to say the model itself if dumb because it does other very hard things so perfectly.
> seven chord groups
This sounds a lot more like Opus 5.0 than Opus 5.5 TBH. I wonder if that was an earlier investigation because 5.5 has improved that kind of language a lot.
- early_exit
Good read! How many pages of text were in scope? I'm not sure if the 1615+1629 pages were the total or just a subagent.
If they were the total I would say it was arguably more impressive the author was able to narrow it down to just 3000 pages than it was to find the dodo mention amongst those!
- jamienk
My dad died and had many many notebooks of his journals with very hard-to-read handwriting. Is it worth the effort to scan all of these so I can feed them in and go to work. Seems like so much minutia is out there, ready to be meta-understood.
- dgellow
What a great read, I generally associate substack with verbose, low quality content, but definitely not the case here!