phoneymouse@lemmy.world to People Twitter@sh.itjust.works · 7 hours agoWhy is no one talking about how unproductive it is to have verify every "hallucination" ChatGPT gives you?lemmy.worldimagemessage-square25fedilinkarrow-up1338arrow-down16
arrow-up1332arrow-down1imageWhy is no one talking about how unproductive it is to have verify every "hallucination" ChatGPT gives you?lemmy.worldphoneymouse@lemmy.world to People Twitter@sh.itjust.works · 7 hours agomessage-square25fedilink
minus-squareohwhatfollyisman@lemmy.worldlinkfedilinkarrow-up6arrow-down2·4 hours agoso, basically, even a broken clock is right twice a day?
minus-squaredev_null@lemmy.mllinkfedilinkarrow-up1·1 hour agoYes, but for some tasks mistakes don’t really matter, like “come up with names for my project that does X”. No wrong answers here really, so an LLM is useful.
minus-squareonionsinmypores@sh.itjust.workslinkfedilinkEnglisharrow-up1·edit-21 hour agoNo, maybe more like, even a functional clock is wrong every 0.8 days. https://superuser.com/questions/759730/how-much-clock-drift-is-considered-normal-for-a-non-networked-windows-7-pc The frequency is probably way higher for most LLMs though lol
so, basically, even a broken clock is right twice a day?
Yes, but for some tasks mistakes don’t really matter, like “come up with names for my project that does X”. No wrong answers here really, so an LLM is useful.
No, maybe more like, even a functional clock is wrong every 0.8 days.
https://superuser.com/questions/759730/how-much-clock-drift-is-considered-normal-for-a-non-networked-windows-7-pc
The frequency is probably way higher for most LLMs though lol