LessWrong 2.0 Reader

And actually, if some of these "short term" issues are not worked on, these issues will likely be forever distractions/barriers, to these populations and family/friends of these population (at some point anyone could be a part of that population), on anything including their own lives, and their life goals (maybe AI safety). 

Western states today use state violence to enforce high taxes and lots of government regulations. In my view they're probably more dominance-oriented than states which just leave rural farmers alone. At least some of this is part of a Keynesian policy to boost economic output, and economic output is closely related to military formidability (due to ability to afford raw resources and advanced technology for the military).

Hm, I guess you would see this as more closely related to bargaining power than to dominance, because in your model dominance is a human-psychology-thing and bargaining power isn't restricted to voluntary transactions?

Question for a lawyer: how is non-reciprocity not an interstate trade issue that federal courts can strike down?

I have attempted to communicate to ultra-high-net-worth individuals, seemingly to little success so far, that given the reality of limited personal bandwidth, with over 99% of their influence and decision-making typically mediated through others, it’s essential to refine the ability to identify trustworthy advisors in each domain. Expert judgment is an active field of research with valuable, actionable insights.

Fascinating. Sounds related to the Yoga concept of kryias.

Opacity: if you could directly inspect an AI’s motivations (or its cognition more generally), this would help a lot. But you can’t do this with current ML models.

The ease with which Anthropic's model organisms of misalignment were diagnosed by a simple and obvious linear probe suggests otherwise. So does the number of elements in SAE feature dictionaries that describe emotions, motivations, and behavioral patterns. Current ML models are no longer black boxes: they rapidly becoming more-translucent grey boxes. So the sorts of applications for this you go on to discuss look like they're rapidly becoming practicable.

You have been attacked by a pack of stray dogs twice?!?!

Can anyone lay out a semi-plausible scenario where humanity survives but isn't dominated by an AI or posthuman god-king? I can't really picture it. I always thought that's what we were going for since it's better than being dead.

Could you please announce these further in advance? Especially given the reading required beforehand it's inconvenient and honestly seems a little inconsiderate.

Great chapter, Great message. +1