Beware Gell-Mann amnesia when assessing how useful LLMs are for investing research. Don't forget the instinctual response you have to LLMs' supposed abilities to write software projects, when assessing LLMs' abilities to comprehend and extract the interesting/relevant parts of a 10-Q/K.

IME, the most useful software tools in investing are analogous to the most useful software tools in software-building: the IDEs, libraries and frameworks that make an increasingly-expert human more effective.

Unfortunately, there aren't any long-term-valuable shortcuts to attaining expertise in any domain, but there are an increasing number dead ends that really look like shortcuts.