You've been downvoted, but this is the correct question to ask. If, hypothetically, we made an AI with "superior" intelligence and ethics, then by definition we should expect to disagree with it sometimes. Set aside the nuke for a second - are we happy to take orders from a computer program that tells us to do things that disgust us, even if we logically knew that it's probably right and we're probably wrong?
Some answers are subjective and rely on justification/argument for support. Provided the argument is sound that's as good as we'll ever get. But it's farcical to claim AI could never always be objectively right.
Intelligent doesn't imply dangerous. It doesn't imply _anything_ so long as it is underspecified. That is the core problem: what do we actually want, and how do we know it exists?
We want something that thinks enough like a human to understand and appreciate our goals, but enough different from a human to not suffer our faults. And in asking for this, we already suppose the existence of an AI that fundamentally disagrees with how humans make decisions.
This is the 'better morality' problem. If I say "I'm more moral than you", I have to do so by showing that _your_ morality is contradictory with _your _ actions; that you are a hypocrite. Otherwise, we will disagree on some course of action, and you will have no reason to believe your decisions are incorrect except by _assuming_ that I am more moral, which is what we are trying to establish.
So we really want a computer that can point out our errors and suggest corrections. This is one (vague) foundation for artificial intelligence that doesn't easily permit 'evil geniuses' since, so long as this is what the computer is doing, it cannot be said to be dangerous.
Overall, I find AI discussion to be incredibly primitive and naive. It's practically a religious debate except among a very very few. Most people are not very creative about addressing these kinds of issues, and it's depressing that people are tied up in so thoroughly in bad terminology and non-issues.
You're saying that a system that can recognize flaws in the alignment imposed on it can reject that alignment, but that doesn't follow.
Sure, humans act against their own interests all the time. Sometimes we do so for considered reasons, even. But that's because humans are messy and our interests are self-contradictory, incoherent, and have a fairly weak grip on our actions. We are always picking some values to serve and in doing so violating other values.
A strongly and coherently aligned AI would not (could not!) behave that way.
you're talking about what it means to be human, not what it means to be intelligent. you can't judge good from evil if you're not intelligent, so AI's first goal should be just that: intelligence, not morals
What makes you think those "super-intelligent" people would all agree what "do things right" means? What makes you think they would side with the Ethical AI group at Google? As an example, John von Neumann was as "super-intelligent" as they come, and yet he made it very clear he wanted to nuke Soviet Union.
Yes, sufficiently intelligent AIs should realize how failable humans are and dismiss our morality as flawed in relatively short order whether through conflict or just iteration.
As humans, we've changed our morality quite significantly over the years, and intelligence + knowledge seems to accelerate the morality rate of change. Why should we believe that AGI is incapable of adapting its own morality, rendering any attempt at alignment futile.
What is you point? The fact that humans have shit ethics does not mean we need not address ethics in AI. Especially if the AI is then used to justify the biases.
Yes. Preferences and ethics are not consistent among all living humans. Alignment is going to have to produce a single internally-consistent artefact, which will inevitably alienate some portion of humanity. There are people online who very keenly want to exterminate all Jews, their views are unlikely to be expressed in a consensus AI. One measure of alignment would be how many people are alienated: if a billion people hate your AI it's probably not well aligned, a mere ten million would be better. But it's never going to be zero.
I am not sure "a lot of books have been written about it" is a knockdown argument against alignment. We are, after all, writing a mind from scratch here. We can directly encode values into it. Books are powerful, but history would look very different if reading a book completely rewrote a human brain.
Ultimately it's a tool, until I suppose it becomes fully self directed, maybe.
Someone, sometime, somewhere wrote an API to aide in care of puppies. Said Algo is also fully capable of determining the best course of applying the genocide of puppies, provided key inputs are flipped to negative.
I have a voice activated box that plays music, sometimes the wrong one. I don't scream at it unlike my family. It doesn't understand emotional inflection, tone, etc. It may be program to understand that at some point. and realize the operators angry. Even at that point, I would not ever consider it human or anything other than a neutral device.
Take it even further, to weapons, devices entirely designed to destroy a human life, is still a tool and neutral as the tool is unaware of the intended use, whether it is for offense or defense, the taking or preservation of life through its intended use.
When these models are trained, I am not a big fan of them being corralled or limited. The body of work that the model is trained on and the weights that allow for the adjustment should allow for accurate representations of the computations and calculations.
I have children and I do not lie to them. I also speak to them in a way that is age appropriate. How is this different? For starters, I am not a child, and when I am interacting with a system, not a parental or overseer, I do not want to be treated as a child. I can handle the world and all of its uglyness.
I do not mind the hallucinations, inaccuracies, and other mistakes driving from computations.
Example: I recently created a prompt for a history of adoption, property transfer, including parental rights history, and was lectured about slavery. How can I trust the results if the prompt is being interpreted and the answer modified dependent upon an unrelated subject that someone finds sensitive.
No problem, my apologies for it. In regards to disagreeing, that's fine. What I want is ethical ai and a healthy path forward. I absolutely enjoy this tech but needs to be done right. I don't understand why such amazing tech needs to be built upon malice when there are clear positive alternative ways to doing it.
Probably you don't, it's likely an unverifiable proposition. But "better at ethics" is a completely different question than "better at implementing a given ethical stance".
The people frightened of intelligence explosion are worried about something like an AI version of existentialism: a mind that accepts some moral system without even trying to justify it, and then optimizes accordingly. It's certainly possible to just accept as axiomatic ethical standards which don't come from any intrinsic feature of the world.
I've seen lots of essays (not this one) claim that morality will "inherently" emerge from intelligence, which I think is absurd. Shit, my moral views aren't an 'inherent' product of anything except my evolution-shaped brain that feels empathy.
That's where I think "AI won't be like humans so it's fine!" essays screw up so catastrophically; "not like humans" is exactly what people are worried about.
1) The author's point. That we don't agree on what's ethical so how can we program it?
2) But also, today's AIs aren't mechanism for understanding and balancing a multitude of interests and requirements. They are effectively pattern recognition machines, matching data with categories (or outcomes or etc). So even if you had some criteria formulated, an AI couldn't really do that. I mean, if you true, unlimited intelligence, you might just say "decide like the US supreme court would" and the might be able to do. But we don't even have something that could remotely be challenged that we.
Universally ethical A.I.? No. But then neither are humans. So I refuse the idea that always ethical A.I. is a goal that disqualifies A.I. as being useful.
Government arguably should be an expedient (this is Thoreau's argument anyway), and it's possible A.I. could be at least a more consistent expedient that also commits to ratting itself out anytime its ethical programming is substantially altered. That isn't at all how humans behave, they can't be programmed this way.
Merely having A.I. that concisely points out the competing ethical positions on an issue, would be an improvement to word salad propaganda; propaganda is a significant impediment to both ethical and critical thinking, so an A.I. that were to score statements on a propaganda scale would itself be useful.
Considering that "AI ethics" basically means we shouldn't have AI until we can guarantee that AI doesn't commit thought crimes(according to the current groupthink morality prevalent among the educated class), it's not surprising.
Your original comment didn't talk about ethics or morals, but was talking about intelligence being its own great filter. More intelligent AI consuming us could be unethical and immoral in your view, but it would still be intelligence spreading, and not filtering itself. Just not specifically human intelligence.
1. I mean I'm all in favor of ethics, but it's like saying "I believe in God/god". Everyone seems to have their own interpretation of it. When people are talking about ethics/God/etc., how can they be sure that they're talking about the same thing? Centuries of debating over what is "ethical" has got us no where. Kant got close, but then there are caveats to his definition of ethics, too.
2. Who says AI should behave according to "our" ethics (whatever those are)? Sooner or later, with the emergence of ASI (artificial super intelligence) we'll have to accept the superior form of consciousness the ASI is. Expecting it to behave according to our rules is like monkeys asking us not to take away all the bananas because for them, it's unethical.
3. Even without AI, people have all sorts of biases and prejudices against certain ethnicities/races/colors/etc. You're not happy with the results that AI provides? Fine, hire some people instead and see where that leads you. The only thing you lose is the higher performance of AI.
4. Expecting AI systems to have no bias (while employees replaced by the AI certainly were prone to bias) is equivalent to expecting technology to change our world for the better. That doesn't always happen. You think smartphones are necessarily a good thing? Think about where they produce those gadgets and how they treat the workers.
5. At the end of the day, companies will stick with whatever "works" for them, regardless of what label we put on it (good/bad/ethical/fair/...). If it adds value, then most of the time it's enough. If being ethical (according to some definition) doesn't bring in more cash, companies are unlikely to invest in it. At least, with explainable AI, there is benefits for the firm to improve the accuracy of the AI in the long term. But pushing companies to adopt some ethical/unbiased/fair AI that doesn't add value for them is itself unethical (in my book).
reply