AlexFromSafeTransition

Message

-11

Existentially relevant thought experiment: To kill or not to kill, a sniper, a man and a button.

There is a room with one window. Inside is a man. On the ceiling there is an interesting button. What happens when it is pressed? Everybody dies, except for the man and 1000 people he gets to pick. The button is not visible from outside the room. The man sometimes...

Aug 14, 2023-18

A way to make solving alignment 10.000 times easier. The shorter case for a massive open source simbox project.

When you have the code that might be an AGI and probably misaligned, how do you test it in a way that is safe? The world has not yet converged on a way to do this. This post attempts to provide an outline of a possible solution. In one sentence:...

Jun 21, 20232

LESSWRONG
LW

LESSWRONG
LW

AlexFromSafeTransition

AlexFromSafeTransition

AlexFromSafeTransition

AlexFromSafeTransition

Existentially relevant thought experiment: To kill or not to kill, a sniper, a man and a button.

A way to make solving alignment 10.000 times easier. The shorter case for a massive open source simbox project.

Existentially relevant thought experiment: To kill or not to kill, a sniper, a man and a button.

A way to make solving alignment 10.000 times easier. The shorter case for a massive open source simbox project.