Majestical-psyche@alien.topB to LocalLLaMAEnglish · 2 years agoLlama 3 will be released in the first quarter of 2024?alien.topimagemessage-square32linkfedilinkarrow-up11arrow-down10file-text
arrow-up11arrow-down1imageLlama 3 will be released in the first quarter of 2024?alien.topMajestical-psyche@alien.topB to LocalLLaMAEnglish · 2 years agomessage-square32linkfedilinkfile-text
minus-squarestddealer@alien.topBlinkfedilinkEnglisharrow-up1·2 years agoPutting “safety” mechanism in foundational models is dumb imo. They are not just text generators, they are statistical models about human languages, and it shouldn’t have made up arbitrary biases about what language should look like.
minus-squareapi@alien.topBlinkfedilinkEnglisharrow-up1·2 years agoIt’s not hard to fine tune base models for any bias you want. “Zero bias” isn’t possible. There’s always some bias in the training data.
minus-squarestddealer@alien.topBlinkfedilinkEnglisharrow-up1·2 years agoSure, but that’s not a reason to purposefully add more biases into it.
Putting “safety” mechanism in foundational models is dumb imo. They are not just text generators, they are statistical models about human languages, and it shouldn’t have made up arbitrary biases about what language should look like.
It’s not hard to fine tune base models for any bias you want. “Zero bias” isn’t possible. There’s always some bias in the training data.
Sure, but that’s not a reason to purposefully add more biases into it.