Re:The leading AI models are now good historians
by dmix on Monday January 27, 2025 @12:05AM
(#42837603)
Couldn’t LLMs cite primary sources much the same way as a textbook or Wikipedia? Which is how you circumvent the biases in textbooks and wikipedia summaries?
Re:The leading AI models are now good historians
by simonw on Monday January 27, 2025 @12:16AM
(#42837664)
A raw LLM is a bad tool for citations, because you can't guarantee that their model weights will contain accurate enough information to be citable.
Instead, you should find the primary sources through other means and then paste them into the LLMs to help translate/evaluate/etc, which is what this author is doing.
Re:The leading AI models are now good historians
by Almondsetat on Monday January 27, 2025 @03:49AM
(#42838838)
Circumventing the bias would mean providing a uniform sampling of the primary sources, which is not guaranteed to happen
The tendency to reaffirm popular beliefs would make current LLMs almost useless for actual historical work, which often involves sifting fact from fiction.