LessWrong 2.0 Reader

Congrats on applying Bayes; unfortunately, you applied it to the wrong numbers.

The key point is that "Question 3: Bayes" is describing a new village, with demographics slightly different to the village in the first half of your post. You grandfathered in the 0.2 from there, when the equivalent number in Village Two is 0.16 (P(Cat) = P(Witch with Cat) + P(Muggle with Cat) = 0.1*0.7 + 0.9*0.1 = 0.07 + 0.09 = 0.16), for a final answer of 43.75%.

(The meta-lesson here is not to trust LLMs to give you info you can't personally verify, and especially not to trust them to check anything.)

This is good news because this is more in line with my original understanding of your post. It's difficult because there are multiple closely related problems of varying degrees of lethality and we had updates on many of them between 2007 and 2023. I'm going to try to put the specific update you are pointing at into my own words.

From the perspective of 2007, we don't know if we can lossilly extracting human values into a convenient format using human intelligence and safe tools. We know that a superintelligence can do it (assuming that "human values" is meaningful), but we also know that if we try to do this with an unaligned superintelligence then we all die.

If this problem is unsolvable then we potentially have to create a seed AI using some more accessible value, such as corrigibility, and try to maintain that corrigibility as we ramp up intelligence. This then leads us to the problem of specifying corrigibility, and we see "Corrigibility is anti-natural to consequentialist reasoning" on List of Lethalities [LW · GW].

If this problem is solvable then we can use human values sooner and this gives us other options. Maybe we can find a basin of attraction around human values [LW · GW] for example.

The update between 2007 and 2023 is that the problem appears solvable. GPT-4 is a safe tool (it exists and we aren't extinct yet) and does a decent job. A more focused AI could do the task better without being riskier.

This does not mean that we are not going to die. Yudkowsky has 43 items on List of Lethalities. This post addresses part of item 24. The remaining items are sufficient to kill us ~42.5 times. It's important to be able to discuss one lethality at a time if we want to die with dignity.

Congrats!

Hu. That is extremely useful. Thank you. 

I've got a lot of singing out of AVM. While my current method works well for this, I find it more challenging than eliciting harmful outputs.

1. It's an arbitrary convention. We could have equally well chosen a convention in which a left hand rule was valid. (Really a whole bunch of such conventions)
2. In the Newtonian 2-point model gravity is a purely radial force and so conserves angular momentum, which means that velocity remains in one plane. If the bodies are extended objects, then you can get things like spin-orbit coupling which can lead to orbits not being perfectly planar if the rotation axes aren't aligned with the initial angular momentum axis.
   If there are multiple bodies then trajectories can be and usually will be at least somewhat non-planar, though energy losses without corresponding angular momentum losses can drive a system toward a more planar state.
   Zero dimensions would only be possible if both the net force and initial velocity were zero, which can't happen if gravity is the only applicable force and there are two distinct points.
   In general relativity gravity isn't really a force and isn't always radial, and orbits need not always be planar and usually aren't closed curves anyway. Though again, many systems will tend to approach a more planar state.

The existence of people like your friend are why the market looks efficient to people like you.

No idea. My favorite stuff is cryptic and self-referential, and I think IQ is a reasonable metric for assessing intelligence statistically, for a group of people [LW · GW].

Also, I don't feel that this article adequately addressed the downside of SA that it accelerates an arms race. SA is only favored when alignment is easy with high probability and you're confident that you will win the arms race, and you're confident that it's better for you to win than for the other guy[1], and you're talking about a specific kind of alignment where an "aligned" AI doesn't necessarily behave ethically, it just does what its creator intends.

[1] How likely is a US-controlled (or, more accurately, Sam Altman/Dario Amodei/Mark Zuckerberg-controlled) AGI to usher in a global utopia? How likely is a China-controlled AGI to do the same? I think people are too quick to take it for granted that the former probability is larger than the latter.

Splitting the Great Idea into parts

Applied to "The Sequences",  or Rationality:

• a collection of good predictive models

• a foundation for a culture more productive and virtuous than mainstream culture

   

• Treating every additional detail as burdensome

It helps to apply scepticism to every post, and internally rank posts by usefulness and credence.

Cooperative Development (CD) is favored when alignment is easy and timelines are longer. [...]

Strategic Advantage (SA) is more favored when alignment is easy but timelines are short (under 5 years)

I somewhat disagree with this. CD is favored when alignment is easy with extremely high probability. A moratorium is better given even a modest probability that alignment is hard, because the downside to misalignment is so much larger than the downside to a moratorium.[1] The same goes for SA—it's only favored when you are extremely confident about alignment + timelines.

[1] Unless you believe a moratorium has a reasonable probability of permanently preventing friendly AI from being developed.