☆ Yσɠƚԋσʂ ☆@lemmy.ml to Technology@lemmy.mlEnglish · 6 months agoHow Game Theory Can Make AI More Reliablewww.wired.comexternal-linkmessage-square4fedilinkarrow-up111arrow-down14
arrow-up17arrow-down1external-linkHow Game Theory Can Make AI More Reliablewww.wired.com☆ Yσɠƚԋσʂ ☆@lemmy.ml to Technology@lemmy.mlEnglish · 6 months agomessage-square4fedilink
minus-square0x0F@lemmy.blahaj.zonelinkfedilinkEnglisharrow-up2·6 months agothat’s so cool, llms seem like they’ll be more useful in a couple years
minus-square☆ Yσɠƚԋσʂ ☆@lemmy.mlOPlinkfedilinkarrow-up3arrow-down1·6 months agoIndeed, if people can figure out how to get LLMs to produce stable outputs and create ways to verify them, then this tech would be a lot more powerful.
minus-squaretechnocrit@lemmy.dbzer0.comlinkfedilinkarrow-up1·edit-26 months agoWe just need a checker AI to check the main AI and then maybe another checker checker AI to check the checker AI… All the way down.
that’s so cool, llms seem like they’ll be more useful in a couple years
Indeed, if people can figure out how to get LLMs to produce stable outputs and create ways to verify them, then this tech would be a lot more powerful.
We just need a checker AI to check the main AI and then maybe another checker checker AI to check the checker AI… All the way down.