While LLMs are better at reading the surrounding context, I am not convinced they are particularly good at taking it on board (compared to an adult human, obviously fantastic compared to any previous NLP).
Biggest failure mode I experience with LLMs is a very human-like pattern, what looks like corresponding with an interlocutor who absolutely does not understand a core point you raised 5 messages earlier and have re-emphasised on each incorrect response:
Biggest failure mode I experience with LLMs is a very human-like pattern, what looks like corresponding with an interlocutor who absolutely does not understand a core point you raised 5 messages earlier and have re-emphasised on each incorrect response:
--
>>> x
>> y
> not y, x
oh, right, I see… y
--
etc.