Would you press the button? The hard problem of alignment
来源: LessWrong ·
There is a TL;DR at the end. The heaven button: You wake up one day and find a button in front of you, with a proof next to it. The proof says that pressing the button will kill everyone on the planet and send them all to heaven. Would you press it? It seems too good to be true. You think it must be a dream. It can't possibly be true. You go through the proof, and it seems correct. But what if you were under the influence of some drug? But the stakes are very high, so you use software you trust to formalize it in Lean, and you run it on a machine you trust. Lean says the proof is correct so no
常见问题
什么是 Would you press the button? The hard problem of alignment？
Would you press the button? The hard problem of alignment is a 文章 discovery curated from LessWrong. There is a TL;DR at the end. The heaven button: You wake up one day and find a button in front of you, with a proof next to it. The proof says that pressing the button will kill ev
如何访问或体验此内容？
You can experience this content directly on its original host (LessWrong) by clicking the "Open Original" button.
此内容来源于哪里？
Curated from LessWrong by the OnSuggest team to surface the most interesting and serendipitous content on the web.
相关发现
所有 文化与思想 发现 →A History of Armistice Day
Podcast Transcript On the eleventh hour of the eleventh day of the eleventh month in 1918, the guns of the First World War fell silent. After four years of unprecedented carnage, the world faced the enormous task of honoring those who had served and died. What began as a commemoration of a single moment in ... Read more
Did Anthony Mackie just let a Doomsday spoiler slip?
Anthony Mackie recently spoke about his involvement in <i> Avengers: Doomsday</i> and said that he enjoyed hanging out with an actor who's not publicly confirmed to be part of the cast.
R.I.P. JoBe Cerny, voice of The Pillsbury Doughboy
JoBe Cerny, best known publicly as the voice of the Pillsbury Doughboy, died on October 30.
You're The Worst creator thinks Hulu is the worst
Stephen Falk didn't take kindly to Hulu removing You're The Worst from streaming without notice.
VisionQuest comes to a pleasant end, but it may get overshadowed by a major MCU development
VisionQuest comes to a pleasant end, but it may get overshadowed by a major MCU development
Rings Of Power time jumps into season three with renewed urgency and questionable choices
The Lord Of The Rings: The Rings Of Power reintroduces itself with a gargantuan premiere filled with unexpected deaths, long-lost loves, and a streamlined sense of impending doom.