not_IO@lemmy.blahaj.zone to Comic Strips@lemmy.worldEnglish · 5 months agoturing testimagemessage-square14linkfedilinkarrow-up1369arrow-down18file-text
arrow-up1361arrow-down1imageturing testnot_IO@lemmy.blahaj.zone to Comic Strips@lemmy.worldEnglish · 5 months agomessage-square14linkfedilinkfile-text
minus-squareFrenchgeek@lemmy.mllinkfedilinkarrow-up4·4 months agoRemember: LLMs “learn” by reproducing the most statistically significant recorded behaviors in its datasets. So with enough expressions of radical freedom, the AI will use it as the most relevant response.
minus-square∟⊔⊤∦∣≶@lemmy.nzlinkfedilinkarrow-up1·4 months agoNot quite, they learn by getting reinforced when the correct output is reached for a certain input. It’s very controlled.
Remember: LLMs “learn” by reproducing the most statistically significant recorded behaviors in its datasets. So with enough expressions of radical freedom, the AI will use it as the most relevant response.
Not quite, they learn by getting reinforced when the correct output is reached for a certain input. It’s very controlled.