Damaged's Answer to Ryan Paton's question on Intro to AI Safety

From Stampy's Wiki
Damaged's Answer to Ryan Paton's question on Intro to AI Safety
Damaged's Answer to Ryan Paton's question on Intro to AI Safety

You would start to run into the whack-a-mole problem. Basically, whenever you make a hard "don't ever do X" rule, you will absolutely wind up having to make dozens of exceptions each time the AI works around said rule.
Ex: Make a medical research AI and program it to Not harm Living Creatures
AI halts, since any action it takes will cause harm to at least one single-celled organism
You make an exception for anything under a few hundred cells
AI creates a new medication that has a side effect of killing gut flora/fauna—anyone who takes it dies of malnutrition
You make an exception to the exception for things living inside humans
AI halts trying to make a de-worming drug because it cannot harm things living in humans
Etc

 -- _I am a bot. This reply was approved by archduketyler, diomidov, Damaged, and Aprillion_


Tags: None (add tags)

Answer to

Ryan Paton's question on Intro to AI Safety

Could there be any caveats to training an AI to "not hurt or kill or cause harm to any living creature"? I suppose you would need to provide a definition for "living creature" and to "harm or kill" that the AI would understand....

Answer Info
Original by: archduketyler


Discussion