How Game Theory Can Make AI More Reliable (www.wired.com)
from yogthos@lemmy.ml to technology@lemmy.ml on 09 Jun 2024 11:16
https://lemmy.ml/post/16658327

#technology

threaded - newest

0x0f@lemmy.blahaj.zone on 09 Jun 2024 14:09 next collapse

that’s so cool, llms seem like they’ll be more useful in a couple years

yogthos@lemmy.ml on 09 Jun 2024 14:21 collapse

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.

technocrit@lemmy.dbzer0.com on 09 Jun 2024 16:21 collapse

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.

DemBoSain@midwest.social on 09 Jun 2024 16:00 collapse

Nope, not playing Card Wars with evil robot Jake.