Sahwa@reddthat.com to Technology@lemmy.worldEnglish · 9 days agoFather sues Google, claiming Gemini chatbot drove son into fatal delusiontechcrunch.comexternal-linkmessage-square202fedilinkarrow-up1297arrow-down15
arrow-up1292arrow-down1external-linkFather sues Google, claiming Gemini chatbot drove son into fatal delusiontechcrunch.comSahwa@reddthat.com to Technology@lemmy.worldEnglish · 9 days agomessage-square202fedilink
minus-squarewonderingwanderer@sopuli.xyzlinkfedilinkEnglisharrow-up5·9 days agoReinforcement Learning from Human Feedback It’s a method of fine-tuning and aligning LLMs which requires active human input
Reinforcement Learning from Human Feedback
It’s a method of fine-tuning and aligning LLMs which requires active human input