An extension of Aumann's approach for reducing game theory to bayesian decision theory to include EDT and UDT like agents 2022-02-09T04:17:40.461Z

Comment by Karl Brisebois (karl-brisebois) on larger language models may disappoint you [or, an eternally unfinished draft] · 2021-11-28T14:52:52.017Z · LW · GW

The fact that language models inevitably will end up contradicting themselves is due to the fact that they have finite memory. Asking them not to contradict themselves over sufficiently large amount of text is asking for the impossible: they're figuring out what to output as the current token by looking at only the last n tokens, so if the contradicting fact lies further back than that there is no way for the model to update on that. And no increase in the size of the models, without fundamental architecture change, will fix that problem.

But architecture changes to deal with that problem might be coming...