- Options
- Login
- Desktop Style
Options
GPT and the Voynich. Code! Not a solution!
- GPT and the Voynich. Code! Not a solution!
-
RE: GPT and the Voynich. Code! Not a solution!
Dunsel > 3 hours ago
So, today's update.
I "think" I got GPT to create a parser that works with Prof. Stolfi's Interlinear file.
And, I found a copy of the You are not allowed to view links. Register or Login to view. by Glen Claston hiding on GitHub and decided to modify my Takahashi parser to work with it.
Once I'm satisfied all these parsers work correctly, I'll start a new thread in this forum and provide links to them and the input files I'm using.
Having produced a few dozen of these particular heatmaps, these look pretty accurate. No huge gaps with missing folios, o and e are the top two characters and the different sections are cleanly visible. The V101 may still need some verification to make sure the letter counts are correct, but it's in the ballpark (edit: checked and the first one was generated with an older version of my parser and, the sorting routine for the x axis was skipping to every 9th column The chart data was correct, just missing a 'few' columns Replaced it with I hope, a chart generated by the correct version).
Here's the output.
Heatmap from the Interlinear LSI
Heatmap from the V101
-
RE: GPT and the Voynich. Code! Not a solution!
bi3mw > 3 hours ago
~ 1986 Struggled with x86 assembler, gave up
~ 1989 Learned PowerBasic, useless today
~ 2012 Since switching to Linux, only Python and shell scripts
I only really used AI to:
- Beautify Python code (works surprisingly well)
- Translate texts from manuscripts (with some hallucinations, but it's getting better)
For all other requests, especially those that are more fact-based, I find the answers too vague and long-winded.
It always boils down to: “I can do XY, do you want me to do that?” -
RE: GPT and the Voynich. Code! Not a solution!
Dunsel > 2 hours ago
(3 hours ago)bi3mw Wrote: You are not allowed to view links. Register or Login to view.~ 1986 Struggled with x86 assembler, gave up
~ 1989 Learned PowerBasic, useless today
~ 2012 Since switching to Linux, only Python and shell scripts
I only really used AI to:
- Beautify Python code (works surprisingly well)
- Translate texts from manuscripts (with some hallucinations, but it's getting better)
For all other requests, especially those that are more fact-based, I find the answers too vague and long-winded.
It always boils down to: “I can do XY, do you want me to do that?”
My job requires I travel a lot. That means I have lots of time to chat with AI. Beats listening to ads on the radio. And yea, that whole question at the end gets REAL annoying. The one I really hate is when I spend the time to build these parsers, I get the prompt wrong, and it slips it's own regex in there because it knows it's faster than the parser. Accuracy be damned.
And, that's why I use Colab. I force it to write out the python to Colab, double check it, have Gemini look it over if I'm uncertain and then... only then... trust the output. And still add in good bit of skepticism.
Had it put out the V101 heatmap and then had it create a table of the letter counts. I immediately realized, the two were different. Found out, the routine to sort the columns did so alphabetically and somehow (it blamed mathematica) it skipped to every 9th column. Trust but verify.