ssillyssadass@lemmy.world to Lemmy Shitpost@lemmy.world · 1 month agoNeed a keyboard with a dedicated "slop" buttonimagemessage-square189linkfedilinkarrow-up1619arrow-down1125
arrow-up1494arrow-down1imageNeed a keyboard with a dedicated "slop" buttonssillyssadass@lemmy.world to Lemmy Shitpost@lemmy.world · 1 month agomessage-square189linkfedilink
minus-squareBonsoir@lemmy.calinkfedilinkarrow-up3arrow-down1·1 month agoThe precomputed matrices are definitely a neural network. GPT literally stands for generative pre-trained transformer, a transformer being a well known neural network architecture.
minus-squareBonsoir@lemmy.calinkfedilinkarrow-up1arrow-down1·1 month agohttps://arxiv.org/pdf/1706.03762
minus-squareBonsoir@lemmy.calinkfedilinkarrow-up1arrow-down1·1 month agoThen explain to me how the neural networks behind LLMs are not mimicking neurons. Because that’s the basic idea behind all of deep learning.
The precomputed matrices are definitely a neural network. GPT literally stands for generative pre-trained transformer, a transformer being a well known neural network architecture.
deleted by creator
https://arxiv.org/pdf/1706.03762
deleted by creator
Then explain to me how the neural networks behind LLMs are not mimicking neurons. Because that’s the basic idea behind all of deep learning.