Mitchell Porter

• Mitchell Porter 7 Apr 2023 8:21 UTC

  1 point

  0 ∶ 0

  on: Chain­ing the evil ge­nie: why “outer” AI safety is prob­a­bly easy

  One can play this game—adding constraints to make a goal safer—with ChatGPT!

  https://​​pastebin.com/​​eQqtPMSr

  It shouldn’t be hard to automate this process, via a GPT-based agent similar to Auto-GPT.