Comment on playing around with desktop ai
hisao@ani.social 4 weeks ago
Interesting. I immediately see first two replies as LLM, third sound like a generic pre-LLM bot autopost, the last one sounds kinda legit. Because it’s so short and forward, it’s really hard for me to see LLM behind it. I don’t know what they’re talking about though, maybe it’s easier to spot the bot from semantics POV.
PixelPilgrim@lemmings.world 4 weeks ago
I get annoyed when it makes post that rephrases the original post, but I think it helps that it’s generic then it’s less offensive and helps it blend in. Keeping it short helps
I’m thinking adding a program that puts in random grammar errors and an AI that does a LLM ai check to filter responses