[callmeal]

>Although it's a no no to anthropomorphize on HN, it's worth noting that some folks think humans are post-hoc rationalizers as well:

There's enough behavioural research to show that it is the case. For ex:

https://www.cambridge.org/core/journals/behavioral-and-brain...

[kfarr]

Thanks, that's a much better example of what I was trying to explain. Again, I'm projecting humanity onto a machine, but it's not a big stretch to imagine that the interaction of attention heads over high-dimensional vectors produces "decisions" that can't be articulated in the moment, only described after the fact in text form.