← Back to context Comment by mcv 17 hours ago To me it explained its inability to follow my preferred coding style by blaming its training data. 4 comments mcv Reply jppittma 11 hours ago I've had better success with having it write and then rewrite rather than trying to prompt the first write into following my style rules. tough 11 hours ago also by abusing linters and other guardrails you can basically automate the rewrite jfb 5 hours ago I mean that’s not abuse? That’s what mechanically checkable invariants are for! They constrain the space the model has to work in. crisnoble 16 hours ago Sounds plausible.
jppittma 11 hours ago I've had better success with having it write and then rewrite rather than trying to prompt the first write into following my style rules. tough 11 hours ago also by abusing linters and other guardrails you can basically automate the rewrite jfb 5 hours ago I mean that’s not abuse? That’s what mechanically checkable invariants are for! They constrain the space the model has to work in.
tough 11 hours ago also by abusing linters and other guardrails you can basically automate the rewrite jfb 5 hours ago I mean that’s not abuse? That’s what mechanically checkable invariants are for! They constrain the space the model has to work in.
jfb 5 hours ago I mean that’s not abuse? That’s what mechanically checkable invariants are for! They constrain the space the model has to work in.
I've had better success with having it write and then rewrite rather than trying to prompt the first write into following my style rules.
also by abusing linters and other guardrails you can basically automate the rewrite
I mean that’s not abuse? That’s what mechanically checkable invariants are for! They constrain the space the model has to work in.
Sounds plausible.