Comment on Hi, Jeffrey!

<- View Parent
brucethemoose@lemmy.world ⁨5⁩ ⁨hours⁩ ago

Meme finetunes are nothing new.

As an example, there are DPO datasets with positive/negative examples intended to train LLMs to respond politely and helpfully (as opposed to the negative response).

And the immediate community though was “…What if I *reversed them?”

source
Sort:hotnewtop