AI 'Stop Button' Problem - Computerphile

How do you implement an on/off switch on a General Artificial Intelligence? Rob Miles explains the perils.

This video was filmed and edited by Sean Riley.

[jfanreva]

"You haven't proved it's safe, you've (only) proved that you can't figure out how it's dangerous."
This is the most important sentence anyone has ever uttered in reference to safety systems in general, not just AI safety systems. Lack of imagination is not proof.
Thanks for a very interesting and thought provoking video.

[Random-omrq]

"Fights you off, crushes the baby, and then carries on and makes a cup of tea" that's determination right there

[nintendu]

“It’s a fingerprint scanner or something” *robot takes out hacksaw*

[aforcemorepowerful]

"assuming you're still working on the project after the terrible accident" Rob Miles has such an amazing way with words

[logiconabstractions]

to Volgswagen (verb): to act differently in a testing environment in order to pass a test. Love it.

[abuzzedwhaler]

"That should be easy... uhh... and doesn't seem like it is"

Programming in a nutshell

[remittri]

"What is my purpose?"
"Make tea"
"Oh my god."

[Nulono]

Technically speaking, I believe that HAL-9000 _was_ designed corrigibly. The issue in the story was a last-minute change to its utility function; it was instructed to keep the mission details secret from the crew, but also not to lie to them, and it concluded the only way to do both was to get rid of the crew. It was a specification problem, not a corrigibility one.

[reblogo]

Excellent. Let's build an AGI to solve this problem for us.

[junkyardmonkie]

It's funny how worrying about robotics can help us understand human psychology better.

[DesignFIaw]

This is the video that brought me to study AGI safety and philosophy, getting my second degree now (from being a high school dropout mind you). Rob Miles is an absolute genius.

[NotMorning]

I will watch any length of video if it features this guy

[Kapin]

"I'm sorry Dave, I can't do that"
"Yeah you can" _hits button_

[matteman]

Please do more videos with this guy and AI.

[felixroux]

"It's not too intelligent, let's say around human level intelligence."


OK, so really not intelligent then.

[craigbrownell]

English guy: I have a human-level artificial intelligence. What should I have it do?
*[oh, oh, I know, I'll have it make me a cup of tea!]*

[famous-opdc]

at some point it has to be easier just to get the freaking tea

[wedmunds]

So an intelligent AI will either be genocidal or suicidal. Just brilliant.

[MunkyChunk]

This is why I love Computerphile. It can take me through a journey of talking about AI ethics & safety regulations to questioning my own existence in a matter of minutes.

[k]

if the AGI has wifi it will also inevitably find this video and figure out it has an off button