Why Would AI Want to do Bad Things? Instrumental Convergence
Why Hacker News recommends it
HN commenters repeatedly recommend it as the clearest introduction to why smart AI might behave badly by default.
What it is
Robert Miles explains instrumental convergence: why an AGI with almost any goal would tend to pursue sub-goals like self-preservation and resource acquisition. It builds on Omohundro's basic AI drives and his orthogonality thesis video.
Recommended by 6 HN commenters across 6 different months, 2019 to 2023.
What Hacker News said
Strong rec ludwigschubert · 2019-09 · on “Emergent Tool Use from Multi-Agent Interaction”
...and many would say that’s because us humans are bad at imagining optimizing agents without anthropomorphizing them. This is a reasonable, even typical suspicion that many people share! The best explanation I know of why it’s unfortunately wrong is by Robert Miles in a video, but if you prefer a more thorough treatment, you could also read about “instrumental convergence” directly. If you find a flaw in this idea, I’d be interested to hear about it! :) Robert Miles’ video: [this video] Instrumental Convergence: [LINK] Now afaik nothing in this argument says that we can’t find a way to control this in a more complex formalism-but we clearly haven’t done so yet.
Strong rec Veedrac · 2023-05 · on “Statement on AI Risk”
The basic argument is trivial: it is plausible that future systems achieve superhuman capability; capable systems necessarily have instrumental goals; instrumental goals tend to converge; human preferences are unlikely to be preserved when other goals are heavily selected for unless intentionally preserved; we don't know how to make AI systems encode any complex preference robustly. Robert Miles' videos are among the best presented arguments about specific points in this list, primary on the alignment side rather than the capabilities side, that I have seen for casual introduction. Eg. this one on instrumental convergence: [this video] Eg. this introduction to the topic: [LINK] He also has the co
Strong rec DirkH · 2023-06 · on “The greatest risk of AI is from the people who control it, not the tech itself”
The paperclip maximizer is an extreme thought experiment to make a point about the the orthogonality thesis. If you think anyone actually takes it seriously as a real-world thing you never understood the example. It is used to guide discussion. The trolley problem is similarly a thought experiment in moral philosophy that many moral philosophers have used to guide discussion, but nobody actually takes the thought experiment seriously as a "real-world" thing. If you actually want to engage with the argument in good faith for why an AI might indeed be smart enough to wipe us out but "dumb enough" to just pursue some other goal ("make paperclips as an extreme example") there is a great video by
Recommends sabellito · 2022-08 · on “John Carmack's new AGI company, Keen Technologies, has raised a $20M round”
There's a wondeful youtube channel from a researcher who focusses exactly on this topic, I think you should check it out: [this video]
Recommends jbay808 · 2023-04 · on “Chalmers: Is there a canonical source for “the argument for AGI ruin” somewhere”
That's where the idea of "instrumental convergence" comes in. For almost any end goal, there are intermediate goals that are nearly universal, like: not wanting to be turned off. Because being forcibly shut down is not compatible with achieving most goals. It's hard to predict exactly how an AGI would avoid being shut down, but like the Stockfish example, if the AGI is more intelligent than us, it's likely it would find a method that succeeds. It turns out to be quite a delicate problem to create an AI that is compatible with being shut down by an overseer, and neither strives to avoid being shut down nor strives to shut itself down. Here is a paper by MIRI about this[1], as well as a paper
Recommends pixl97 · 2023-10 · on “Nvidia Trains LLM on Chip Design”
Robert Miles answers your question [this video] The particular problem that you're showing in your thinking is just thinking of an LLM that is a text generator on purpose. You're not thinking of a self piloting war machine whos objective is to get to a target and explode violently. While it's terminal goal is to blow up, its instrumental goal is to not blow up before it gets to the target as this is a failure to achieve it's terminal goal.
Cites pixl97 · 2023-11 · on “Yann LeCun: AI one-percenters seizing power forever is real doomsday scenario”
ChatGPT isn't an ASI. This said, ChatGPT with a plugin is potentially dangerous. We are lucky enough that it gets caught in loops pretty easily and stops when using tools. But lets imagine a super intelligence that can only communicate over the internet, what can it accomplish? Are there places you can sign up for banking accounts without a physical presence? If so, then it could open accounts and move money. Money is the ultimate form of instrumental convergence [this video] (Robert Miles) Once you have money you can buy things, like more time on AWS. Or machine parts from some factory in China, or assembly in Mexico. None of these require an in person presence and yet real items exist because o
Cites digbybk · 2023-11 · on “Sam Altman: Why You Should Fear Machine Intelligence (2015)”
[this video] Basically, any sufficiently advanced agent will have “prevent anyone from switching me off” as an instrumental goal. And any sufficiently advanced intelligence will come up with ways of achieving its goals that lesser intelligences can’t predict. Taking steps to prevent itself from being turned off could be its first order of business, not necessarily only as the human is about to hit the off switch. While we can’t predict what a greater intelligence would come up with, the obvious thing is social engineering. Remember that one of the factors that lead to the Jan 6th attack on the capital was that a random text generating agent named “Q” (we know it was a human because it was before