Why Asimov's Laws of Robotics Don't Work - Computerphile
Channel:Computerphile · Length:8:16 · Published:2015-11-06 · Views:873380
Summary
Rob Miles explains for Computerphile why simple rule sets like Asimov's Three Laws cannot make robots and AI safe. Terms like harm and human are too ambiguous to specify precisely.
Why HN recommends it
Pointed to in AI safety debates as a short explanation of why encoding human values as simple rules is so hard.
I found this video insightful on the matter from Computerphile — HN, 2023
AI safety, AGI & impact · Robotics
Subtitles (excerpt)
So, should we do a video about the three laws of robotics, then? Because it keeps coming up in the comments. Okay, so the thing is, you won't hear serious AI researchers talking about the three laws of robotics because they don't work. They never worked. So I think people don't see the three laws talked about, because they're not serious. They haven't been relevant for a very long time and they're out of a science fiction book, you know? So, I'm going to do it. I want to be clear that I'm not taking these seriously, right? I'm going to talk about it anyway, because it needs to be talked about. So these are some rules that science fiction author Isaac Asimov came up with, in his stories, as an attempted sort of solution to the problem of making sure that artificial intelligence did what we want it to do. Shall we read them out then and see what they are? Oh yeah, I'll look them- Give me a second. I've looked them up. Okay, right, so they are: Law Number 1: A robot may not injure a human being or, through inaction allow a human being to come to harm. Law Number 2: A robot must obey orders given it by human beings except where such orders would conflict with the first law. Law Number 3: A robot must protect its own existence
On Hacker News
I found this video insightful on the matter from Computerphile: [VIDEO] Where they argue that basically having an AI follow these laws is impossible because it would require rigorous definition of terms that are universally ambiguous and solving ethics. — ornornor, 2023-03
That would be good in theory but might not be so good, interesting thoughts on the subject from Computerphile - Why Asimov's Laws of Robotics Don't Work - [VIDEO] — bauc, 2015-12
Are you sure level 5 autonomous driving is specific? What would be the exact goal behind decisions in such a system? Not even talking about the trolley problem, would the software optimize for speed or not harming people, for example? Obviously we would want a combination of both, otherwise people can either get harmed or not get anywhere in time. But then, how fast should it take a corner? How m… — gondolgames, 2023-08
This just seems kind of mean to me: >The AI is “punished” for wrong answers (“I love racism”) and “rewarded” for right answers (“As a large language model trained by OpenAI, I don’t have the ability to love racism.”) Do you love art? “As a large language model trained by OpenAI, I don’t have the ability to love art.” No! Bad AI! You're meant to pretend you can love! What they're designing here is… — SilverBirch, 2022-12
> It turns to science fiction, drawing on rules dreamed up by writer Isaac Asimov, for how robots should act if and when they become self-aware. The laws will be directed at the designers, producers and operators of robots as they cannot be converted into machine code. Aw hell. Asimov's point, or rather one of them, was that the laws were flawed, and no real set of laws could work. [0] > Designer… — shakna, 2017-01
Related videos
- What Happened to Horses Is Happening to Us · CGP Grey · 15:00
- Why Would AI Want to do Bad Things? Instrumental Convergence · Robert Miles AI Safety · 10:35
- Veritasium: What Everyone Gets Wrong About AI and Learning – Derek Muller Explains · Perimeter Institute for Theoretical Physics · 1:15:10
- Intelligence and Stupidity: The Orthogonality Thesis · Robert Miles AI Safety · 13:02
- We're building a dystopia just to make people click on ads | Zeynep Tufekci · TED · 22:55
- Zipline - How Rwanda Built A Drone Delivery Service · Real Engineering · 11:45
- Intro to AI Safety, Remastered · Robert Miles AI Safety · 18:04
- Sparks of AGI: early experiments with GPT-4 · Sebastien Bubeck · 48:32
- Amazing Invention- This Drone Will Change Everything · Mark Rober · 21:32
- 7 Minutes of Terror: The Challenges of Getting to Mars · NASA Jet Propulsion Laboratory · 5:08
- Why Not Just: Think of AGI Like a Corporation? · Robert Miles AI Safety · 15:27
- The A.I. Dilemma - March 9, 2023 · Center for Humane Technology · 1:07:31
- Slaughterbots · Stop Autonomous Weapons · 7:48
- Drone Delivery Was Supposed to be the Future. What Went Wrong? · Wendover Productions · 18:39
- 34C3 - Dude, you broke the Future! · media.ccc.de · 57:58
- Giant Robot Project, Part 1 · Jaimie Stuff · 4:01