Lena@gregtech.eu to Programmer Humor@programming.devEnglish · 23 hours ago"Source code file"gregtech.euimagemessage-square160fedilinkarrow-up1645arrow-down19
arrow-up1636arrow-down1image"Source code file"gregtech.euLena@gregtech.eu to Programmer Humor@programming.devEnglish · 23 hours agomessage-square160fedilink
minus-squareZetta@mander.xyzlinkfedilinkarrow-up2·edit-25 hours agoPerfect, groks context limit is 256,000, and as we all know llm recal only gets better as context fills so you will get perfect slop that works amazingly /s and more info on quality drop with context increase here https://github.com/NVIDIA/RULER
minus-squarehperrin@lemmy.calinkfedilinkEnglisharrow-up1·4 hours ago250,000 lines is way more than 250,000 tokens, so even that context is too small.
Perfect, groks context limit is 256,000, and as we all know llm recal only gets better as context fills so you will get perfect slop that works amazingly
/s and more info on quality drop with context increase here https://github.com/NVIDIA/RULER
250,000 lines is way more than 250,000 tokens, so even that context is too small.