Skip to content
Hallway
0:00 / 0:00

#orthogonalitythesis#aisafety#aialignment

Intelligence and Stupidity: The Orthogonality Thesis

Robert Miles AI Safety

174K subscribers • 9 videos on Hallway

YouTube
  • Recommended by 6 people: 6 on Hacker News.
  • Presented by Robert Miles
  • May be out of date. Uploaded 8 years ago, in an area where tools change fast.

Beginner. No background in the topic needed.

710K views8 years ago6 recommendations

AI and machine learningAI safety and impactComputation and complexity

Robert Miles explains the orthogonality thesis, which states that an artificial intelligence can have any level of intelligence combined with any goal.

Can highly intelligent agents have stupid goals? A look at The Orthogonality Thesis and the nature of stupidity. The 'Stamp Collector' Computerphile video: youtube.com/watch?v=tcdVC4e6EV4 My other Computerphile videos: youtube.com/watch?v=GSIDS_lvRv4&list=PLqL14ZxTTA4fRMts7Af2G8… Katie Byrne's Channel: youtube.com/channel/UCwA5wd50HYLa-ZY80LSAg3w Chad Jones' Channel: youtube.com/user/cjone150 patreon.com/robertskmiles With thanks to my wonderful Patreon supporters: - Steef - Sara Tjäder - Jason Strack - Chad Jones - Stefan Skiles - Ziyang Liu - Jordan Medina - Jason Hise - Manuel Weichselbaum - 1RV34 - James McCuen - Richárd Nagyfi - Ammar Mousali - Scott Zockoll - Ville Ahlgren - Alec Johnson - Simon Strandgaard - Joshua Richardson - Jonatan R - Michael Greve - robertvanduursen - The Guru Of Vision - Fabrizio Pisani - Alexander Hartvig Nielsen - Volodymyr - David Tjäder - Paul Mason - Ben Scanlon - Julius Brash - Mike Bird - Tom O'Connor - Gunnar Guðvarðarson - Shevis Johnson - Erik de Bruijn - Robin Green - Alexei Vasilkov - Maksym Taran - Laura Olds - Jon Halliday - Robert Werner - Roman Nekhoroshev - Konsta - William Hendley - DGJono - Matthias Meger - Scott Stevens - Emilio Alvarez - Michael Ore - Dmitri Afanasjev - Brian Sandberg - Einar Ueland - Lo Rez - Marcel Ward - Andrew Weir - Taylor Smith - Ben Archer - Scott McCarthy - Kabs Kabs - Phil - Tendayi Mawushe - Gabriel Behm - Anne Kohlbrenner - Jake Fish - Bjorn Nyblad - Stefan Laurie - Jussi Männistö - Cameron Kinsel - Matanya Loewenthal - Wr4thon - Dave Tapley - Archy de Berker - Kevin - Vincent Sanders - Marc Pauly - Andy Kobre - Brian Gillespie - Martin Wind - Peggy Youell - Poker Chen patreon.com/robertskmiles

Why it's here

6 people recommend this

What people say. Highly recommended as an exceptionally clear explanation of the orthogonality thesis and the core challenges of AI alignment.

Moments people linked to

pegasuson Hacker News • Recommends

On “Show HN: GPT-4 Reverse Turing Test”

…rs into practice. If that ends up causing some "minor" problems, should we confine the software for one thousand years in an air-gapped enclosure, until it learns a bitter lesson? Or should we take to task the careless Maker of the bot? To me, the answer is obvious. PS: this video to me states the problem in a nutshell (that whole channel is gold) link to this video…
View on Hacker News

pegasuson Hacker News • Recommends

On “Show HN: GPT-4 Reverse Turing Test”

Yes, I believe some careful and informed pondering leads one towards that conclusion. Hume's guillotine is an implacable philosophical device: link to this video (I warmly recommend all the content on that delightfully frightening channel)
View on Hacker News

simonhon Hacker News • Recommends

On “OpenAI chief goes before US Congress to propose licenses for building AI”

That’s the alignment problem. We don’t know what the actual goals of an AI trained neural net are. We know what criteria we trained it against, but it turns out that’s not at all the same thing. I highly recommend Rob Miles channel on YouTube. Here’s a good one, but they’re all fascinating. It turns out training an AI to have the actual goals we want it to have is fiendishly difficult. link to this video
View on Hacker News

casebashon Hacker News • Recommends

On “Show HN: Help, I let GPTChat control my computer”

Given that you've already updated your views recently, perhaps you'd be open to reconsidering whether AI could form an existential risk? One of the best talks (but more technical talks) I've seen on this topic is Evan Hubringer's "How likely is deceptive alignment". link It may also be worthwhile checking out the Rob Miles video on the Orthogonality Thesis - link to this video
View on Hacker News

circuit10on Hacker News • Recommends

On “Pausing AI Developments Isn't Enough. We Need to Shut It All Down”

> How does that process go from where it's at today to "alien hive mind"? Without passing through "develop advanced codes of ethics and morality" etc? Why do you think it would do that? It will understand human ethics perfectly but that doesn’t mean it will follow them, because human morals aren’t a universal objective truth. This is a good video explaining that: link to this video
View on Hacker News

pegasuson Hacker News • Recommends

On “Simply explained: How does GPT work?”

…vation. By definition, any goal it has can only be the goal of whoever designed that system. Even if its maker decides - "let it pick goals randomly", those randomly picked goals are just intermediate steps toward the enacting of the programmer's original goal. Robert Miles' YouTube videos on alignment shed light on these issues also. For example: link to this video Another relevant source on these issues is the book "The Master and his Emissary", which discusses how basically the language center can, in some way - I'm simplifying a lot, fall prey to the illusion that "it" is the entirety of human consciousness. * or at least some subsystems of that language center, it's important to remember how littl…
View on Hacker News

mitthrowaway2on Hacker News • Recommends

On “BabyAGI: An Autonomous and Self-Improving Agent”

…g returns and there isn't enough compute globally to do produce a hypothetical AGI. What makes you think LLMs have reached a point of diminishing returns? So far, the benchmarks are continuing to show accelerating returns, to the point that it's becoming difficult for benchmarks to keep up.3 1: Hume's Law, AKA the Is-Ought problem: link 2: link to this video 3: "Foundation models and the next era of AI", Microsoft Research, link…
View on Hacker News

circuit10on Hacker News • Recommends

On “Universal Paperclips”

…we aren't superintelligent so it's hard to gain enough control and power and plan well enough to do it that well > talking about a goal that has sub-human-intelligence sophistication There is no reason a simple goal can't be followed in an intelligent way or vice versa. This is called the "orthogonality thesis". There's a good video about it here: link to this video…
View on Hacker News

circuit10on Hacker News • Recommends

On “Universal Paperclips”

> The basic premise is that it has somewhere in it that is telling it to make more paperclips. Put the constraints there. What constraints do you suggest? If it's just changing "make as many paperclips as possible" to "make at least x number of paperclips", here's a good explanation of why that doesn't really work: link > If you're saying such an AI would be too smart to be a simple paperclip maximizer No, that's not what I'm saying. Any goal is compatible with any level of intelligence, there is no reason why it wouldn't be possible to follow a simple goal in a complex way. Again here's a video about that: link to this video
View on Hacker News

AstroBenon Hacker News • Recommends

On “AGI Is Still 30 Years Away – Ege Erdil and Tamay Besiroglu”

> Isn’t just the ability to preform a task. Right. In this case I'd say it's the ability to interpret data and use it to succeed at whatever goals it has Evaluating emotional context would be similar to a chess engine calculating its next move. There's nothing there that implies a conscience, sentience, morals, feelings, suffering or anything 'human'. It's just a necessary intermediate function to achieve its goal Rob miles has some really good videos on AI safety research which touches on how AGI would think. Thats shaped a lot of how I think about it link to this video
View on Hacker News

Colin Tayloron Artificial Intelligence Stack Exchange • Mentions

On “What are the different types of goals for an AI system called?”

AI researcher Rob Miles uses the terms 'terminal goal' and 'instrumental goal' for the first and second types respectively. I'm not sure if these are standard parlance in the field, however Rob explains them in this video: link to this video
4View the answer

NumberWangManon Hacker News • Mentions

On “If AI scaling is to be shut down, let it be for a coherent reason”

…nt to do. They want to do it because they want to. The goal is not smart or stupid, it just is. It may be different from your goal, and hard to understand. Now consider that an AI is not even human. Is it that much of a stretch to imagine that it has a goal as alien, or more, than the weirdest human goal you can think of? *edit - as in this video: link to this video…
View on Hacker News

ahartmetzon Hacker News • Mentions

On “Google DeepMind CEO Demis Hassabis is stepping down”

One could also say that a logical agent needs ultimate goals to do anything and it cannot choose them by logical means. link to this video
View on Hacker News