Comment by _0ffh
4 years ago
And no wonder, as they correspond much closer to a Kahneman system 1 than system 2, where we do most of our math.
4 years ago
And no wonder, as they correspond much closer to a Kahneman system 1 than system 2, where we do most of our math.
Btw, here's an example of how even a very simple zero-shot/prompt-engineering attempt to introduce a bit of system 2 reasoning into a language model can improve results.
https://arxiv.org/abs/2201.11903