Re:GPT-4 gets a B on my quantum computing final exam
by whazor on Tuesday April 11, 2023 @05:45PM
(#35532033)
A big factor is that the error rate is compounding. Tiny mistakes would become bigger and bigger if you would run GPT in a loop.
It needs interaction and calibration from a human to keep it in check. Even we as humans are using all kinds of different feedback mechanisms to validate our thought process.
Though this might be a different way of hooking GPT up to reality.
It needs interaction and calibration from a human to keep it in check. Even we as humans are using all kinds of different feedback mechanisms to validate our thought process.
Though this might be a different way of hooking GPT up to reality.