Identity

Browsing as: Guest_20

Login

Register New User

Canonizer

Canonizer:

Algorithm Information

As Of

include review

default

as of (yy/mm/dd):

Navigation

Help

Canonizer Main

What Is The Canonizer

Browse

Create New Topic

Upload File

Canonizer Sorted Camp Tree
Camp Statement

The term "friendliness", when used of an AI, isn't intended to indicate friendliness in the same sense we mean it of people. Instead, it means that the AI has a deep and unchangeable disposition to treat humans well, regardless of how the AI evolves over subsequent generations.

An AI that is ignorant or uncaring of our interests - or one that could evolve in that direction - could do humans enormous damage.

The mission of the friendly AI project is to find ways to design AIs so that, even though AIs will be able to improve themselves and re-write their own source code, the AIs will maintain their "friendly" attitude at all times.

Support Tree for "FriendlyAIisSensible" Camp

Total Support for This Camp (including sub-camps): 1.5

0.5 robomoon - Delegate Your Support
Current Topic Record:

Topic Name: Friendly AI Importance

Name Space:

Current Camp Record:

Camp Name: FriendlyAIisSensible

Title: Desire for friendly AI is sensible and laudable

Key Words:

URL:

Parent Camp: Agreement