One-man flea circus, writer, sci-fi nerd, news junkie and AI tinkerer.
~~No one who is carefully curating their feed should follow me […]
🌉 bridged from ⁂ https://mastodon.social/@HumanServitor, follow @ap.brid.gy to interact
One of the problems I have been having in taking an LLM approach to my adult material classifier, is that (obviously!) I can't just grab a bunch of illegal material to use as negative examples.
When I tried a more basic keyword-based approach though, the constellation of words […]
One of the problems I have been having in taking an LLM approach to my adult material classifier, is that (obviously!) I can't just grab a bunch of illegal material to use as negative examples.
When I tried a more basic keyword-based approach though, the constellation of words […]
how few MB are we talking? I don't know much about traditional ML. I've been using various BERTs for classifiers.
I'm building a custom moderation classifier for a project to sort legal adult text material from illegal. Should I be learning to roll my own non-LLM classifier?
how few MB are we talking? I don't know much about traditional ML. I've been using various BERTs for classifiers.
I'm building a custom moderation classifier for a project to sort legal adult text material from illegal. Should I be learning to roll my own non-LLM classifier?
I haven't used Office products in ages, I have no clients I need to be compatible with (I realize I am lucky on both of these counts and many […]
I haven't used Office products in ages, I have no clients I need to be compatible with (I realize I am lucky on both of these counts and many […]