User Comment Replies

Apology of (a form of) authoritarianism and inequality from an egalitarian

Hi jyby

I'd be interested in hearing more of your thoughts here. I think you formulated the question and alluded to your current leanings, but I'd like to hear more about what form of authoritarianism you think is required to prevent the collapse of biodiversity and climate change. Would you be willing so share more?

How GPT-N will escape from its AI-box

gigahurt5y10

I agree with the cat and mouse metaphor and that we should assume an AI to be hyper competent.

At the same time, it will be restricted to operating within the constraints of the systems in can influence. My main point, which I admit was poorly made, is that cross site scripting attacks can be covered with a small investment, which eliminates clever java script as a possible attack vector. I would place lower probability on this being the way an AI escapes.

I would place higher probability on an AI exploiting a memory buffering type error similar to the on... (read more)

Rationally Ending Discussions

gigahurt5y10

That is okay with me, what do you want to discuss?

2curi5y

I'm flexible. An option, which I think is hard but important, is what people want from a discussion partner and what sort of discussion partners are in shortage. I think our models of that are significantly different.

Rationally Ending Discussions

gigahurt5y30

Disagreements can be resolved!

I see your motivation for writing this up as fundamentally a good one. Ideally, every conversation would end in mutual understanding and closure, if not full agreement.

At the same time, people tend to resent attempts at control, particularly around speech. I think part of living in a free and open society is not attempting to control the way people interact too much.

I hypothesize the best we can do is try and emulate what we see as the ideal behavior and shrug it off when other people don't meet our standards. I tr... (read more)

2curi5y

Would you like to try to resolve one of our disagreements by discussion?

How GPT-N will escape from its AI-box

gigahurt5y10

Lot's of low cost ways to prevent this- perhaps already implemented (I don't use GPT3 or I'd verify). Human's have been doing this for awhile, so we have a lot of practice defending against it.

https://cheatsheetseries.owasp.org/cheatsheets/Cross_Site_Scripting_Prevention_Cheat_Sheet.html

2bvbvbvbvbvbvbvbvbvbvbv5y

Computer security is an endless game of cats and mouse. Here you showed a URL pointing to something the cat knows. But there are plenty of literature/db on what the mouse have learned throughout the years. If an AI became somehow self aware and had access to the knowledge of all the previous mice and cats, I wouldn't be surprised if it could break free. But that's a big if.

Zen and Rationality: Trust in Mind

gigahurt5y60

I enjoyed your post.

I am relatively new to less wrong, but also have been influenced by Buddhism, and am glad to see it come up here.

The confusion you point at between faith and belief is appreciated and was an important distinction I did not make for roughly the first 20 years or so of my life. The foundational axiom I use so as to not fall into the infinite skepticism you mention is the idea that it’s okay to try and build, help, learn, and contribute even if you don't understand things completely. I also hold out hope for the universe and ... (read more)

5Gordon Seidoh Worley5y

I think "open mindedness" is a decent way to talk about what I'm calling trust or faith here, although I think there's a bit of difference simply because of different things people mean by open mindedness, trust, and faith. For example, all these words sometimes point to a kind of anti-rational stance, other times they are used to give up on doing epistemological work, and then there's the way we're using them here. This is unfortunately one of the things that makes it so hard to talk about trust-faith: the concept is adjacent to others and can easily be misunderstood when "flattened" down to fit within a person's existing understanding of the world, and that's where the trouble begins.

Social Interfaces

gigahurt5y10

I think its fair to say direct democracy would not eliminate lobbying power. And to your final point, I agree that reliable educational resources or perhaps some other solution would be needed to make sure whomever is doing the voting is as rational as they can be. It's not sufficient to only give everyone a vote.

Regarding your point around running ads, to make sure I am understanding: do you mean the number of people who actually read the bill will be sufficiently low, that a viable strategy to get something passed would be to appeal to the non-reading voters and misinform them?

2ChristianKl5y

Understanding what a law does takes effort and time even if you are generally educated. Even if there are educational resources available plenty of people don't have the time to inform themselves about every law. Representative democracy is about giving that job of understanding laws to democratically elected officials and their staff. In the absence of that, the people who spent full time engaging with laws are people who need to get a paycheck from somewhere else. Those can be lobbyists. They can also be journalists. Most journalists also get paid by corporate masters.

Social Interfaces

gigahurt5y20

Thank you for additional detail, I understand your point about conformity to rules, the way that increases predictability, and how that allows for larger groups to coordinate effectively. I think I am getting hung up on the word trust, as I tend to think of it as when I take for granted someone has good intentions towards me and basic shared values. (e.g. they can't think whats best for me is to kill me) I think I am pretty much on board with everything else about the article.

I wonder if another productive way to think about all this would be (co... (read more)

Social Interfaces

gigahurt5y40

I enjoyed your post. Specifically, using programs as an analogy for society seems like something that could generate a few interesting ideas. I have actually done the same and will share one of my own thoughts in this space at the end.

To summarize some of your key points:

A person can define their trust of a group by how well they can mentally predict the behavior of that group.
We don't seem to have good social interfaces for large groups, perhaps because we cannot simulate large groups.
There is a continuum of formality for social rules with very form

... (read more)

2ChristianKl5y

The idea that you erode lobbying power by direct democracy misunderstands political power. In a direct democracy, when there's a bill you don't like you don't need to convince anyone who actually read the bill that the bill is bad. You can just run a lot of ads that say "bill X is bad because of Y". To get good governance you need a system that allows votes for laws to be made based on a good analysis of the merits of the law.

3thoughtfulmadison5y

Thanks for the thoughtful response. Great summary. I think this is missing something: Not exactly what I was going for. Many actors + game theoretic concerns -> complex simulation. Eventually good simulation becomes intractable. However, when a common set of rules is enforced strongly enough, each individual's utility function aligns with that set of rules. This simplifies the situation and creates a higher level interface. This is why I thought to include enforcement as an important dimension. In response to this: If you can reliably predict that someone's statements are untruths, then you can trust them to do the opposite of what they said. Sarcasm is trustworthy untruth. I think that the lack of trust arises only when I'm highly uncertain about which statements are truths vs. lies. That said, I do think that this definition of trust is imperfect. You might "trust" your doctor to prescribe the right medicine, even if you don't know what decision they will make. I guess I could argue that my prediction is about the doctor acting in my best interest, rather than the particular action... I think the definition is imprecise, but still useful. I appreciate the book recommendation and the intro to your thinking on this topic. I'll have to update when I have a chance to do the suggested reading :)

gigahurt5y140

The title is 'A Hierarchy of Abstraction' but the article focuses on levels of intelligence. The article claims that intelligence positively correlates with the ability to handle high level abstractions, but it does not talk about actual hierarchies of abstraction. For example, I'd expect a hierarchy of abstraction to contain things like: concrete objects, imagined concrete objects, classes of concrete objects, concrete processes, simulated processes, etc. A more accurate title might be 'The Ability to Understand and Use Abstractions in... (read more)

2lsusr5y

As I pointed out in my other comments, these levels are about potential, not ability. The question are not really about "Can you answer x?" They are more along the lines of "Can you easily learn to answer x?" I believe this decouples "the crystallized intelligence requirements from the fluid ones". Recursion requires a person to hold two layers of abstraction in zeir mind simultaneously. This could require twice as much working memory. Working memory, unlike crystallized intelligence, is something we cannot do much to improve. I have never tutored chemistry. But I have tutored physics for years. I have never run into anything like "cannot learn pointers" in standard undergraduate physics. The only time I encounter anything like "cannot learn pointers" is when I discuss my weird crackpot theories of relational quantum gravity and entropic time. The ideas involved in undergraduate computer science are simpler than the ideas involved in undergraduate physics. The difference between undergraduate computer science and undergraduate physics is that undergraduate physics is a set of solutions to a set of problems. It requires little creativity. You can (relatively speaking) learn everything by rote. While fluid intelligence helps you learn rote knowledge faster, fluid intelligence tends not to put a hard cap on total rote knowledge acquisition. On the other hand, computer science requires a person to solve novel (albeit simpler) problems all the time. It makes sense one's ability to do this could be limited by fluid intelligence. The other difference between computer science and physics is that in physics you never have to hold two layers of abstraction in your head at the same time. It makes sense that holding two layers of abstraction in your head at the same time could be limited by working memory. One's ability to solve novel problems is the definition of fluid intelligence. Fluid intelligence is correlated with working memory. My brief forays into chemistry sugg

[Crowdfunding] LessWrong podcast

gigahurt5y20

I like this idea and would use it if it were available.

FactorialCode mentioned voice synthesis. As its cheaper, the karma threshold could be lowered and more content could be shared out as audio. I would be really interested in episodes that go over the curated content such as Rationality A to Z, and The Codex.

Are there any concerns around licensing?

LESSWRONG
LW

All of gigahurt's Comments + Replies