[throw310822]

> conclude that LLMs exhibit failures across many axes we'd find to be demonstrative of AGI.

Which LLMs? There's tons of them and more powerful ones appear every month.

[alansaber]

True but the fundamental architecture tends not to be radically different, it's more about the training/RL regime

[throw310822]

But the point is that to even start to claim that a limitation holds for all LLMs you can't use empirical results that have been demonstrated only for a few old models. You either have a theoretical proof, or you have empirical results that hold for all existing models, including the latest ones.