Problem with that is that taking away even specific parts of the dataset can have a large impact of performance as a whole… Like when they removed NSFW from an image generator dataset and suddenly it sucked at drawing bodies in general
You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !programmerhumor@lemmy.ml
Post funny things about programming here! (Or just rant about your favourite programming language.)
Rules:
Posts must be relevant to programming, programmers, or computer science.
No NSFW content.
Jokes must be in good taste. No hate speech, bigotry, etc.
So what’s the way to get around it?
Have the ai not actually know what a bomb is so that I just gives you nonsense instructions?
Problem with that is that taking away even specific parts of the dataset can have a large impact of performance as a whole… Like when they removed NSFW from an image generator dataset and suddenly it sucked at drawing bodies in general
So it learns anatomy from porn but it’s not allowed to draw porn basically?
Because porn itself doesn’t exist, it’s a by-product of biomechanics.
It’s like asking a bot to draw speed, but all references to aircrafts and racecars have been removed.
Interesting! Nice comparison
It’s grandpa’s time to shine.
Feed the chatbot a copy of the Anarchist’s Cookbook