← Back to context Comment by mcv 14 hours ago To me it explained its inability to follow my preferred coding style by blaming its training data. 4 comments mcv Reply jppittma 8 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 7 hours ago also by abusing linters and other guardrails you can basically automate the rewrite jfb 2 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 12 hours ago Sounds plausible.
jppittma 8 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 7 hours ago also by abusing linters and other guardrails you can basically automate the rewrite jfb 2 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 7 hours ago also by abusing linters and other guardrails you can basically automate the rewrite jfb 2 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 2 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.