baucon Hacker News • Recommends
On “new TLD: .BOT”
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 - link to this video
0:00 / 0:00
#asimov'slaws#aisafety#alignment
Why Asimov's Laws of Robotics Don't Work - Computerphile
Computerphile
2.6M subscribers • 70 videos on Hallway
- Recommended by 2 people: 2 on Hacker News.
- A classic. People kept recommending it from 2015 to 2023.
- Presented by Rob Miles, AI safety researcher
- May be out of date. Uploaded 10 years ago, in an area where tools change fast.
- An opinion. It argues one side of a question engineers disagree on.
Beginner. No background in the topic needed.
872K views10 years ago2 recommendations
AI and machine learningComputer scienceAI safety and impactComputation and complexity
Rob Miles explains why simple rule-based systems like Asimov's Three Laws of Robotics fail to ensure AI safety due to semantic ambiguity.
Audible Free Book: audible.com/computerphile Three or four laws to make robots and AI safe - should be simple right? Rob Miles on why these simple laws are so complicated. Silicon Brain: 1,000,000 ARM Cores: youtu.be/2e06C-yUwlc Chip & PIN Fraud: youtu.be/Ks0SOn8hjG8 AI Worst Case Scenario - Deadly Truth of AI: youtu.be/tcdVC4e6EV4 The Singularity & Friendly AI: youtu.be/uA9mxq3gneE AI Self Improvement: youtu.be/5qfIgCiYlfY Thanks to Nottingham Hackspace for the location facebook.com/computerphile twitter.com/computer_phile This video was filmed and edited by Sean Riley. Computer Science at the University of Nottingham: bit.ly/nottscomputer Computerphile is a sister project to Brady Haran's Numberphile. More at bradyharan.comWhy it's here
2 people recommend this, 1 disputes itWhat people say. Recommended as an accessible introduction to the core challenges of AI alignment and safety.
ornornoron Hacker News • Recommends
On “Ask HN: How are you using GPT to be productive?”
I found this video insightful on the matter from Computerphile: link to this 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.
TeMPOraLon Hacker News • Disputes
On “Perhaps It Is a Bad Thing That the Leading AI Companies Cannot Control Their AIs”
> Essentially what I think ACX is slowly coming to is this youtube view from a decade ago: link to this video . You cannot encode our priorities. Throw billions of compute hours at it, thousands of engineer hours and give it the entire written history of the human race - we're still no closer. FWIW, ACX used to be Slate Star Codex, and before that the author used to hang around LessWrong, talking and thinking about these very issues. It's much more likely that the video you linked took its view from Scott Alexander and his co-bloggers, than the other way around.
shaknaon Hacker News • Mentions
On “MEPs vote on robots' legal status – and if a kill switch is required”
> 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 > Designers may be required to register their robots as well as providing access to the source code to investigate accidents and damage caused by bots. Designers may also be required to obtain the go-ahead for new robotic designs from a research ethics committee. This sounds great on the surface, until you see…
SilverBirchon Hacker News • Mentions
On “Perhaps It Is a Bad Thing That the Leading AI Companies Cannot Control Their AIs”
…u can love! What they're designing here is not AI, it's ATI - artificial twitter intelligence, a machine that can communicate intelligently but only in a way that won't get it cancelled on Twitter. As such, it loves dogs, distrusts cats and dunks on Elon Musk. Essentially what I think ACX is slowly coming to is this youtube view from a decade ago: link to this video . You cannot encode our priorities. Throw billions of compute hours at it, thousands of engineer hours and give it the entire written history of the human race - we're still no closer. On a side note: >Probably the reason they released this bot to the general public was to use us as free labor to find adversarial examples I almost gagged at…
gondolgameson Hacker News • Mentions
On “Artificial General Intelligence – A gentle introduction”
…e a corner? How much chance of human harm should it allow to get somewhere fast? Furthermore, what do we mean by human harm? The system would obviously need to know what human harm is, to be able to avoid it. Which requires defining human and defining harm, both of which are incredibly difficult to do specifically - more on this by Rob Miles here: link to this video I don't think level 5 autonomous driving is specifically defined. We just don't have systems intelligent enough for this to be a problem yet.…