Using AI to do research - Specifically online searching

[Linda]

I would be tempted to try to produce a complete and exhaustive bibliography of every early 15th century cipher that I know of and then feed this bibliography into an AI and ask it to find me an early 15th century cipher not in my bibliography. However, I am not sure that would be productive.

I fed it your comment above and it said 3 problems that might interfere: training data wall, hallucination risk, and un-digitized reality, and suggests you ask it to find correlations with merchant marks, alchemical symbols and administrative abbreviations, suggesting that boring docs are more likely to hold the key than some secret cipher that has yet to be found. I asked it to do that and it just blathered on and was not productive, mostly due to hallucinations, wrong assumptions (it keeps thinking there are plants in quire 20, for instance, even though i have corrected it before on that particular hallucination) and a lack of specificity in its answers, which could be related to my not being specific enough also.