alt Hacker NewsThe entire point of LLMs is that they produce statistically average results, so of course you're going to have problems getting them to produce non-average code.
The entire point of LLMs is that they produce statistically average results, so of course you're going to have problems getting them to produce non-average code.
they (are supposed to) produce average on average, and the output distribution is (supposed to be) conditioned on the context