LessWrong 2.0 Reader

I liked the ending of this story.

From the related book Elephant in the Brain:

Here is the thesis we’ll be exploring in this book: We, human beings, are a species that’s not only capable of acting on hidden motives—we’re designed to do it. Our brains are built to act in our self-interest while at the same time trying hard not to appear selfish in front of other people. And in order to throw them off the trail, our brains often keep “us,” our conscious minds, in the dark. The less we know of our own ugly motives, the easier it is to hide them from others.

In the same way that Chinese people forget how to write characters by hand, I think most programmers will forget how to write code without LLM editors or plugins pretty soon.

Very powerful reasoning. I would add that a relevant form of self-deception that should be investigated in this framework is religious faith, given its place as as foundational to societies worldwide. 

Religious faith seems like an optimal form of solution to hostile telepaths problem, in certain contexts it seems like a mixture of the three solutions you outlined. (Newcomblike self-deception, Having power and Occlumency)

Religious faith seems to provide psychological power through feelings of absolute certainty and over-confidence that religious people experience.  At the same time, the conversion to religions is correlated with overcoming PTSD and addiction (step 2 of the 12 steps program: "Came to believe that a Power greater than ourselves could restore us to sanity.")

I think there is an underlying problem of concept hierarchy which may precede self deception. Maybe we are able to hide concepts and thoughts while they occupy a peripheral part of the mind, this could be also linked to a continuous formulation of the newcomb-like problem in decision theory. I am not sure how this unfolds, will be trying to explore that in the weeks to come. 

Thank you for sharing!

Oh, these are good objections. Thanks!

I'm inclined to 180 on the original statements there and instead argue that predictive modelling works because, as Pearl says, "no correlation without causation". Then an important step when basing decisions on predictive modelling is verifying that the intervention has not cut off the causal path we depended on for decision-making.

Do you think that would be closer to the truth?

Talking to people is often useful for goals like "making friends" and "sharing new information you've learned" and "solving problems" and so on. If what conversation means (in most contexts and for most people) is "signaling that you repeatedly have interesting things to say", it's required to learn to do that in order to achieve your other goals.

Most games aren't that intrinsically interesting, including most social games. But you gotta git gud anyway because they're useful to be able to play well.

Hm. This rings true... but also I think that selecting [vibes, in this sense] for attention also selects against [things that the other person is really committed to]. So in practice you're just giving up on finding shared commitments. I've been updating that stuff other than shared commitments is less good (healthy, useful, promising, etc.) than it seems.

See also: https://www.lesswrong.com/posts/zSNLvRBhyphwuYdeC/ai-86-just-think-of-the-potential [LW · GW] -- @Zvi [LW · GW] 

"The result is a mostly good essay called Machines of Loving Grace, outlining what can be done with ‘powerful AI’ if we had years of what was otherwise relative normality to exploit it in several key domains, and we avoided negative outcomes and solved the control and alignment problems..."

"This essay wants to assume the AIs are aligned to us and we remain in control without explaining why and how that occured, and then fight over whether the result is democratic or authoritarian."

"Thus the whole discussion here feels bizarre, something between burying the lede and a category error."

"...the more concrete Dario’s discussions become, the more this seems to be a ‘AI as mere tool’ world, despite that AI being ‘powerful.’ Which I note because it is, at minimum, one hell of an assumption to have in place ‘because of reasons.’"

"Assuming you do survive powerful AI, you will survive because of one of three things.

1. You and your allies have and maintain control over resources.
2. You sell valuable services that people want humans to uniquely provide.
3. Collectively we give you an alternative path to acquire the necessary resources.

That’s it."

"The right answer is that intuitions, especially those that say or come from ‘the future will be like the past’ are not to be trusted here."

Ok but how do you deal with the tragedy of the high dimensionality of context-space? People worth thinking with have wildly divergent goals--and even if you share goals, you won't share background information.

...How is that definition different than a realtime version of what you do when participating in this forum?