SuspciousCarrot78@lemmy.world to Privacy@lemmy.ml · edit-23 months agoI made my LLM stop bullshitting. Nothing leaves your machine.codeberg.orgexternal-linkmessage-square18linkfedilinkarrow-up171arrow-down19file-textcross-posted to: privacy@lemmy.ml
arrow-up162arrow-down1external-linkI made my LLM stop bullshitting. Nothing leaves your machine.codeberg.orgSuspciousCarrot78@lemmy.world to Privacy@lemmy.ml · edit-23 months agomessage-square18linkfedilinkfile-textcross-posted to: privacy@lemmy.ml
minus-squareScoffingLizard@lemmy.dbzer0.comlinkfedilinkarrow-up1·4 months agoSo basically, you created a prompt wrapper that removes position bias by using trust to evaluate both, and forcing an evidence path with scratch. This is a really cool development. It probably will not solve everything but it solves alot. Is llama open source?
minus-squareSuspciousCarrot78@lemmy.worldOPlinkfedilinkarrow-up3·edit-23 months agodeleted by creator
So basically, you created a prompt wrapper that removes position bias by using trust to evaluate both, and forcing an evidence path with scratch. This is a really cool development. It probably will not solve everything but it solves alot.
Is llama open source?
deleted by creator