Using Opus 5.5 to discover a new eyewitness record of the dodo

There is a avenue of potential, eh, danger, for want of a better word. Maybe "risk" is better, when "decoding" models are pointed at some religious texts.

Religious texts that people live by religiously. And to be clear, all major "book" religions could be at risk here, I'm not snidley pointing at one here.

> 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.

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!

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.

What a great read, I generally associate substack with verbose, low quality content, but definitely not the case here!

[flagged]