Possibly linux@lemmy.zip to MeanwhileOnGrad@sh.itjust.worksEnglish · 15 天前Me poking Deepspeak-r1 with a stick...lemmy.zipimagemessage-square27fedilinkarrow-up1105arrow-down18
arrow-up197arrow-down1imageMe poking Deepspeak-r1 with a stick...lemmy.zipPossibly linux@lemmy.zip to MeanwhileOnGrad@sh.itjust.worksEnglish · 15 天前message-square27fedilink
minus-squareboredtortoise@lemm.eelinkfedilinkEnglisharrow-up1·15 天前Yes. Every model has its overlords altering information. It’d be fine if models would be only instructed to avoid harmful content generation on ethical grounds but it’s quite different from being developed to produce fabrications on purpose.
Yes. Every model has its overlords altering information. It’d be fine if models would be only instructed to avoid harmful content generation on ethical grounds but it’s quite different from being developed to produce fabrications on purpose.