penudddff

• penudddff 27 Mar 2023 3:05 UTC

  2 points

  0

  on: Steel­man­ning OpenAI’s Short-Timelines Slow-Take­off Goal

  “What if we get to the 2020s and it turns out all the powerful AI are LLMs?”

  Did you mean 2030’s, or am I misinterpreting something?

• penudddff 24 Mar 2023 2:04 UTC

  5 points

  4

  in reply to: Lucas Pfeifer’s comment on: con­tinue work­ing on hard al­ign­ment! don’t give up!

  I dont think the most likely way is gaining access to autonomous weapons designed to kill. An ai smarter than all humans has many different options to take over, including making its own autonomous weapons