Hacker News new | ask | show | jobs
by dcl 2 days ago
One question I have about stuff like this: How does it affect the models intelligence or thinking ability. If this modifies the output or chain of thought in any way, it may impact what the model is capable of right? Especially if it's not trained to use this kind of language during training.
1 comments

It definitely seems like this should be a post processing layer instead of an instruction.