I’ve found Gemini overwhelmingly terrible at pretty much everything, it responds more like a 7b model running on a home pc or a model from two years ago than a medium commercial model in how it completely ignores what you ask it and just latches on to keywords… It’s almost like they’ve played with their tokenisation or trained it exclusively for providing tech support where it links you to an irrelevant article or something

The issue for RPGs is that they have such “small” context windows, and a big point of RPGs is that anything could be important, investigated, or just come up later

Although, similar to how deepseek uses two stages (“how would you solve this problem”, then “solve this problem following this train of thought”), you could have an input of recent conversations and a private/unseen “notebook” which is modified/appended to based on recent events, but that would need a whole new model to be done properly which likely wouldn’t be profitable short term, although I imagine the same infrastructure could be used for any LLM usage where fine details over a long period are more important than specific wording, including factual things

Or avoid a decrease in profit, which is why you get so many posturing bandwagons which slow down once enough people have forgotten that it won’t affect profits anymore, eg all the statements and policy, name, logo etc changes due to BLM in mid-late 2020