Possibly linux@lemmy.zip to MeanwhileOnGrad@sh.itjust.worksEnglish · 2 months agoMe poking Deepspeak-r1 with a stick...lemmy.zipimagemessage-square26fedilinkarrow-up1107
arrow-up1107imageMe poking Deepspeak-r1 with a stick...lemmy.zipPossibly linux@lemmy.zip to MeanwhileOnGrad@sh.itjust.worksEnglish · 2 months agomessage-square26fedilink
minus-squareboredtortoise@lemm.eelinkfedilinkEnglisharrow-up1·2 months agoYes. 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.