LESSWRONG
LW

All of alexsalt's Comments + Replies

1Gyrodiot
Winners have just been announced here.
Announcing the AI Alignment Prize
alexsalt20

My entry:

Raising Moral AI

Is it easier to teach a robot to stay safe by not tearing off its own limbs and not drilling holes in its head and not touching lava and not falling from a cliff and so on ad infinitum, or introduce pain as inescapable consequence of such actions and let robot experiment and learn?

Similarly, while trying to create a safe AGI, it is futile to make exhaustive and non-contradictory set of rules (values, policies, laws, committees) due to infinite complexity. A powerful AGI agent might find an exception or conflict in rules and... (read more)

Reply
0Justus Eapen
I don't see why this has been downvoted so many times. It is likely to be the only way of ensuring the value-alignment we seek. It is based on ancient wisdom (cut the trees that bear bad fruit) and prioritizes safety by cordoning off AGI agents.