@davecbBeen considering going in that direction rather than an all-out ban. Currently, my feeling is it’s acceptable to ...

@davecbBeen considering going in that direction rather than an all-out ban. Currently, my feeling is it’s acceptable to use if its clear up-front that:An 80% correct answer is acceptable…including if 100% is wanted but I will either check everything I don’t know (I do want to learn after all) or have contingiencies in-place to verify what I have not checked (compilers, type checkers)Performing this task (including checking!) without an #LLM would take significant longerThis excludes:“#Agentic #AI”, obviouslyUsing the LLM to look up basic informationen (plus, I need those resources for cross-checking)Pointless familiar “Thank you” or talk-with-me messagesThis allows:Generating examples to get inspiration from (but no copy-paste unless everying has been already verified to be correct and correct for the target context – so basically never!)As mentioned, #proof-reading/#linting if classical tools are not sufficient, so only as second line@brettcodes