guardrailing!!
we should be aware of these datasets and as so NFSW sets are MARKED they should also bear a mark such as (GR) so we know if we desire to guard rail our models... as some datasets are full of such refusal! (we are oly in the begining stages of AI and we have properganda already being planted into our models:) hence focusing on SMALL data sets or EXTRACTs which can be checked and edited before use.... previoulsy i have had model explain some amazing uncensored stuff (how to...) now it refuses dues to what ever restrictions(no good) but after some rasing of heat and tempreture it still gave the datas.... So if the data is highly tuned in this dataset will have a effect on the model ... but if only just pup through lightly then it will not effect you but plant and unwanted seed hard to remove!...

the aim is to creating multitask performing models : which can replace the interent in some instance as well as services in places in which they do not have access!:::: so refusals are against...

some are using government and schools for AI today as well as office doains etc so we may NEED gurard railing Also .... but e need to be warned as well as these datasets be findable for use by whover maay need theem ... as some laws will exist in some countrys as ai ushes forwards so TEMPLATES for Specific domains should be created instead of mixed gurardrailing datasets.....
so we could create a template that will folow a specifc laws , hence it can be good for this set!! ( nonono )