AI "Stop Button" Problem - Computerphile
1.4M views · Mar 3, 2017 · Education
Comments · 5.3K
@DanTheStripe · 2 weeks ago
This might be about to get a lot of views.
38
@Random-om8rq · 7 years ago
"Fights you off , crushes the baby , and then carries on and makes a cup of tea" that's determination right there
2.8K
@aforcemorepowerful · 5 years ago
"assuming you're still working on the project after the terrible accident" Rob Miles has such an amazing way with words
297
@Nulono · 3 years ago
Technically speaking, I believe that HAL-9000 <i>was</i> 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.
196
@jfan4reva · 8 years ago (edited)
"You haven't proved it's safe, you've (only) proved that you can't figure out how it's dangerous." <br>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.<br>Thanks for a very interesting and thought provoking video.
3.6K
@abuzzedwhaler7949 · 7 years ago
"That should be easy... uhh... and doesn't seem like it is" <br><br>Programming in a nutshell
1.4K
@logiconabstractions6596 · 7 years ago
to Volgswagen (verb): to act differently in a testing environment in order to pass a test. Love it.
2K
@Twisted_Code · 7 years ago (edited)
So essentially, we're trying to figure out how to not make a sociopath. Brilliant...
371
@remittri · 9 years ago
"What is my purpose?"<br>"Make tea"<br>"Oh my god."
2.7K
@Kapin05 · 7 years ago (edited)
"I'm sorry Dave, I can't do that"<br>"Yeah you can" <i>hits button</i>
268
@reblogo · 9 years ago
Excellent. Let's build an AGI to solve this problem for us.
1.3K
@DesignFIaw · 3 years ago (edited)
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.
157
Up next
Stop Button Solution? - Computerphile
Computerphile · 499K views
The AI Language We Can't Read: Neuralese ft. Rob Miles - Computerphile
Computerphile · 588K views
Prompting Is Dead in 6 Months. Andrew Ng, Stanford
philia · 239K views
The Insane Real Engineering of the Nazi Enigma Machine
Veritasium · 14M views
Trump Falls Asleep on Live TV, Tells the Truth for First Time & Our Favorite Foxtrotter Guillermo!
Jimmy Kimmel Live · 4.7M views
Training Sand to Think: Artificial General Intelligence & Future of Physics
Perimeter Institute for Theoretical Physics · 289K views
Why AI Tokens are so Expensive - Computerphile
Computerphile · 822K views
Has a Millennium Prize Problem been solved by AI?
Stand-up Maths · 1.2M views
Casey Muratori – The Big OOPs: Anatomy of a Thirty-five-year Mistake – BSC 2025
Better Software Conference · 903K views
Why a Language Map of the World is Impossible
Map Men · 4.7M views
How Watermarks Track AI Generated Content - Computerphile
Computerphile · 497K views
Bill Gates: A.I. ‘Makes Nuclear Weapons Look Like Nothing’ | The Ezra Klein Show
The Ezra Klein Show and 2 more · 814K views
The Uncomfortable Truth About AI “Reasoning” | World Science Festival
World Science Festival · 640K views
A Response to Steven Pinker on AI
Robert Miles AI Safety · 215K views
Casey Muratori – The Root of The Root of All Evil – BSC 2026
Better Software Conference and Molly Rocket · 403K views
The OTHER AI Alignment Problem: Mesa-Optimizers and Inner Alignment
Robert Miles AI Safety · 272K views
ChatGPT Whistleblower: They Offered Me $2m To Keep Quiet, No One Is Ready For What's Coming!
The Diary Of A CEO · 19M views
AI & Logical Induction - Computerphile
Computerphile · 365K views
AI Isn't as Powerful as We Think | Hannah Fry
New Scientist · 1.3M views
AI is MUTATING: And We Don't Know What It is Doing | Connor Leahy
The Peter McCormack Show · 1.6M views
Philosopher David Chalmers asks: When we talk to AI, what are we talking to?
UC Berkeley and Berkeley Arts & Humanities · 206K views
The Race to Harness Quantum Computing's Mind-Bending Power | The Future With Hannah Fry
Bloomberg Originals · 9.6M views
Intro to AI Safety, Remastered
Robert Miles AI Safety · 206K views
Concrete Problems in AI Safety (Paper) - Computerphile
Computerphile · 206K views
Will AI outsmart human intelligence? - with 'Godfather of AI' Geoffrey Hinton
The Royal Institution · 820K views
General AI Won't Want You To Fix its Code - Computerphile
Computerphile · 412K views