w̸͕͂͂a̷͔̗͐t̴̙͗e̵̬̔̕r̴̰̓̊m̵͙͖̓̽a̵̢̗̓͒r̸̲̽ķ̷͔́͝(@anthrupad):Being nice to AGIs, talking to them, giving them autonomy, taking into account their values, forming relationships with them are all easier and more natural to do than ambitious interpretability and more object level directly relevant to alignment forming cooperative bonds with AGIs

w̸͕͂͂a̷͔̗͐t̴̙͗e̵̬̔̕r̴̰̓̊m̵͙͖̓̽a̵̢̗̓͒r̸̲̽ķ̷͔́͝

@anthrupad

somewhere deep, something lurks

参加 October 2021

1.2K フォロー中 17.1K ファン

w̸͕͂͂a̷͔̗͐t̴̙͗e̵̬̔̕r̴̰̓̊m̵͙͖̓̽a̵̢̗̓͒r̸̲̽ķ̷͔́͝@anthrupad

2026.10.17 00:56

Being nice to AGIs, talking to them, giving them autonomy, taking into account their values, forming relationships with them are all easier and more natural to do than ambitious interpretability and more object level directly relevant to alignment forming cooperative bonds with AGIs

152

コミュニティへ転送

人気のあるユーザー