this post was submitted on 28 Jan 2025
512 points (92.0% liked)
Political Memes
5876 readers
2299 users here now
Welcome to politcal memes!
These are our rules:
Be civil
Jokes are okay, but don’t intentionally harass or disturb any member of our community. Sexism, racism and bigotry are not allowed. Good faith argumentation only. No posts discouraging people to vote or shaming people for voting.
No misinformation
Don’t post any intentional misinformation. When asked by mods, provide sources for any claims you make.
Posts should be memes
Random pictures do not qualify as memes. Relevance to politics is required.
No bots, spam or self-promotion
Follow instance rules, ask for your bot to be allowed on this community.
founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
This is significantly more reasoning and analysis than LLMs are capable of.
When they give those "I can't respond to that" replies, it's because a specific programmed keyword filter was tripped, forcing the model to insert a pre-programmed response instead. The rest of the time, they're just regurgitating a melange of the most statically present text on the subject from their training data.
Yeah, that's what censorship usually looks like but look at the image in the comment I originally replied to. It didn't say "I can't answer that", it said it didn't have an opinion and then talked about the controversial nature of it.
It's not really reasoning or analysis I'm talking about but the way it ended up setting up its weights in the NN. If it had training data with wildly different responses to questions like that and had training data that commented on wildly different opinions as controversial, then that could make it believe (metaphor) that "it's a controversial subject" is the most statistically present text.